diff --git a/docs/Makefile b/docs/Makefile index 37b2bda76..fe062fc76 100644 --- a/docs/Makefile +++ b/docs/Makefile @@ -19,3 +19,7 @@ help: %: Makefile @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) +intl: + sphinx-intl build + @$(SPHINXBUILD) -b html -D language=zh_CN "$(SOURCEDIR)" "$(BUILDDIR)/html/zh-cn" $(SPHINXOPTS) $(O) + diff --git a/docs/README.md b/docs/README.md index 1e4de2bd9..68edc4dbe 100644 --- a/docs/README.md +++ b/docs/README.md @@ -11,13 +11,14 @@ pip install -r requirements-docs.txt # Build the docs. make clean make html -``` -## Open the docs with your browser +# Build the docs with translation +make intl -```bash +# Open the docs with your browser python -m http.server -d _build/html/ ``` -Launch your browser and open http://localhost:8000/. - +Launch your browser and open: +- English version: http://localhost:8000 +- Chinese version: http://localhost:8000/zh_CN diff --git a/docs/requirements-docs.txt b/docs/requirements-docs.txt index 2d18af238..b8d3ac77e 100644 --- a/docs/requirements-docs.txt +++ b/docs/requirements-docs.txt @@ -7,3 +7,4 @@ sphinx-togglebutton myst-parser msgspec sphinx-substitution-extensions +sphinx-intl \ No newline at end of file diff --git a/docs/source/conf.py b/docs/source/conf.py index 551c3b27d..e354ef993 100644 --- a/docs/source/conf.py +++ b/docs/source/conf.py @@ -88,8 +88,8 @@ templates_path = ['_templates'] # # This is also used if you do content translation via gettext catalogs. # Usually you set "language" from the command line for these cases. -language = 'en' - +locale_dirs = ['locale/'] +gettext_compact = False # List of patterns, relative to source directory, that match files and # directories to ignore when looking for source files. # This pattern also affects html_static_path and html_extra_path. diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/community/contributors.po b/docs/source/locale/zh_CN/LC_MESSAGES/community/contributors.po new file mode 100644 index 000000000..4f5b7bf8d --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/community/contributors.po @@ -0,0 +1,1647 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../community/contributors.md:1 +msgid "Maintainers and contributors" +msgstr "维护者和贡献者" + +#: ../../community/contributors.md:3 +msgid "Maintainers" +msgstr "维护者" + +#: ../../community/contributors.md +msgid "Name" +msgstr "名称" + +#: ../../community/contributors.md +msgid "Github ID" +msgstr "Github 账号" + +#: ../../community/contributors.md +msgid "Date" +msgstr "日期" + +#: ../../community/contributors.md +msgid "Xiyuan Wang" +msgstr "Xiyuan Wang" + +#: ../../community/contributors.md +msgid "[@wangxiyuan](https://github.com/wangxiyuan)" +msgstr "[@wangxiyuan](https://github.com/wangxiyuan)" + +#: ../../community/contributors.md +msgid "2025/01" +msgstr "2025/01" + +#: ../../community/contributors.md +msgid "Yikun Jiang" +msgstr "Yikun Jiang" + +#: ../../community/contributors.md +msgid "[@Yikun](https://github.com/Yikun)" +msgstr "[@Yikun](https://github.com/Yikun)" + +#: ../../community/contributors.md +msgid "2025/02" +msgstr "2025/02" + +#: ../../community/contributors.md +msgid "Yi Gan" +msgstr "Yi Gan" + +#: ../../community/contributors.md +msgid "[@ganyi1996ppo](https://github.com/ganyi1996ppo)" +msgstr "[@ganyi1996ppo](https://github.com/ganyi1996ppo)" + +#: ../../community/contributors.md +msgid "Shoujian Zheng" +msgstr "Shoujian Zheng" + +#: ../../community/contributors.md +msgid "[@jianzs](https://github.com/jianzs)" +msgstr "[@jianzs](https://github.com/jianzs)" + +#: ../../community/contributors.md +msgid "2025/06" +msgstr "2025/06" + +#: ../../community/contributors.md:12 +msgid "Contributors" +msgstr "贡献者" + +#: ../../community/contributors.md:14 +msgid "" +"vLLM Ascend every release would not have been possible without the following" +" contributors:" +msgstr "每个 vLLM Ascend 版本的发布都离不开以下贡献者：" + +#: ../../community/contributors.md:16 +msgid "Updated on 2025-06-10:" +msgstr "更新于 2025-06-10：" + +#: ../../community/contributors.md +msgid "Number" +msgstr "数字" + +#: ../../community/contributors.md +msgid "Contributor" +msgstr "贡献者" + +#: ../../community/contributors.md +msgid "Commit ID" +msgstr "提交 ID" + +#: ../../community/contributors.md +msgid "83" +msgstr "83" + +#: ../../community/contributors.md +msgid "[@ZhengWG](https://github.com/)" +msgstr "[@ZhengWG](https://github.com/)" + +#: ../../community/contributors.md +msgid "2025/7/7" +msgstr "2025/7/7" + +#: ../../community/contributors.md +msgid "" +"[3a469de](https://github.com/vllm-project/vllm-" +"ascend/commit/9c886d0a1f0fc011692090b0395d734c83a469de)" +msgstr "" +"[3a469de](https://github.com/vllm-project/vllm-" +"ascend/commit/9c886d0a1f0fc011692090b0395d734c83a469de)" + +#: ../../community/contributors.md +msgid "82" +msgstr "82" + +#: ../../community/contributors.md +msgid "[@wm901115nwpu](https://github.com/)" +msgstr "[@wm901115nwpu](https://github.com/)" + +#: ../../community/contributors.md +msgid "" +"[a2a47d4](https://github.com/vllm-project/vllm-" +"ascend/commit/f08c4f15a27f0f27132f4ca7a0c226bf0a2a47d4)" +msgstr "" +"[a2a47d4](https://github.com/vllm-project/vllm-" +"ascend/commit/f08c4f15a27f0f27132f4ca7a0c226bf0a2a47d4)" + +#: ../../community/contributors.md +msgid "81" +msgstr "81" + +#: ../../community/contributors.md +msgid "[@Agonixiaoxiao](https://github.com/)" +msgstr "[@Agonixiaoxiao](https://github.com/)" + +#: ../../community/contributors.md +msgid "2025/7/2" +msgstr "2025/7/2" + +#: ../../community/contributors.md +msgid "" +"[6f84576](https://github.com/vllm-project/vllm-" +"ascend/commit/7fc1a984890bd930f670deedcb2dda3a46f84576)" +msgstr "" +"[6f84576](https://github.com/vllm-project/vllm-" +"ascend/commit/7fc1a984890bd930f670deedcb2dda3a46f84576)" + +#: ../../community/contributors.md +msgid "80" +msgstr "80" + +#: ../../community/contributors.md +msgid "[@zhanghw0354](https://github.com/zhanghw0354)" +msgstr "[@zhanghw0354](https://github.com/zhanghw0354)" + +#: ../../community/contributors.md +msgid "" +"[d3df9a5](https://github.com/vllm-project/vllm-" +"ascend/commit/9fb3d558e5b57a3c97ee5e11b9f5dba6ad3df9a5)" +msgstr "" +"[d3df9a5](https://github.com/vllm-project/vllm-" +"ascend/commit/9fb3d558e5b57a3c97ee5e11b9f5dba6ad3df9a5)" + +#: ../../community/contributors.md +msgid "79" +msgstr "79" + +#: ../../community/contributors.md +msgid "[@GDzhu01](https://github.com/GDzhu01)" +msgstr "[@GDzhu01](https://github.com/GDzhu01)" + +#: ../../community/contributors.md +msgid "2025/6/28" +msgstr "2025/6/28" + +#: ../../community/contributors.md +msgid "" +"[de256ac](https://github.com/vllm-project/vllm-" +"ascend/commit/b308a7a25897b88d4a23a9e3d583f4ec6de256ac)" +msgstr "" +"[de256ac](https://github.com/vllm-project/vllm-" +"ascend/commit/b308a7a25897b88d4a23a9e3d583f4ec6de256ac)" + +#: ../../community/contributors.md +msgid "78" +msgstr "78" + +#: ../../community/contributors.md +msgid "[@leo-pony](https://github.com/leo-pony)" +msgstr "[@leo-pony](https://github.com/leo-pony)" + +#: ../../community/contributors.md +msgid "2025/6/26" +msgstr "2025/6/26" + +#: ../../community/contributors.md +msgid "" +"[3f2a5f2](https://github.com/vllm-project/vllm-" +"ascend/commit/10253449120307e3b45f99d82218ba53e3f2a5f2)" +msgstr "" +"[3f2a5f2](https://github.com/vllm-project/vllm-" +"ascend/commit/10253449120307e3b45f99d82218ba53e3f2a5f2)" + +#: ../../community/contributors.md +msgid "77" +msgstr "77" + +#: ../../community/contributors.md +msgid "[@zeshengzong](https://github.com/zeshengzong)" +msgstr "[@zeshengzong](https://github.com/zeshengzong)" + +#: ../../community/contributors.md +msgid "" +"[3ee25aa](https://github.com/vllm-project/vllm-" +"ascend/commit/192dbbcc6e244a8471d3c00033dc637233ee25aa)" +msgstr "" +"[3ee25aa](https://github.com/vllm-project/vllm-" +"ascend/commit/192dbbcc6e244a8471d3c00033dc637233ee25aa)" + +#: ../../community/contributors.md +msgid "76" +msgstr "76" + +#: ../../community/contributors.md +msgid "[@sharonyunyun](https://github.com/sharonyunyun)" +msgstr "[@sharonyunyun](https://github.com/sharonyunyun)" + +#: ../../community/contributors.md +msgid "2025/6/25" +msgstr "2025/6/25" + +#: ../../community/contributors.md +msgid "" +"[2dd8666](https://github.com/vllm-project/vllm-" +"ascend/commit/941269a6c5bbc79f6c1b6abd4680dc5802dd8666)" +msgstr "" +"[2dd8666](https://github.com/vllm-project/vllm-" +"ascend/commit/941269a6c5bbc79f6c1b6abd4680dc5802dd8666)" + +#: ../../community/contributors.md +msgid "75" +msgstr "75" + +#: ../../community/contributors.md +msgid "[@Pr0Wh1teGivee](https://github.com/Pr0Wh1teGivee)" +msgstr "[@Pr0Wh1teGivee](https://github.com/Pr0Wh1teGivee)" + +#: ../../community/contributors.md +msgid "" +"[c65dd40](https://github.com/vllm-project/vllm-" +"ascend/commit/2fda60464c287fe456b4a2f27e63996edc65dd40)" +msgstr "" +"[c65dd40](https://github.com/vllm-project/vllm-" +"ascend/commit/2fda60464c287fe456b4a2f27e63996edc65dd40)" + +#: ../../community/contributors.md +msgid "74" +msgstr "74" + +#: ../../community/contributors.md +msgid "[@xleoken](https://github.com/xleoken)" +msgstr "[@xleoken](https://github.com/xleoken)" + +#: ../../community/contributors.md +msgid "2025/6/23" +msgstr "2025/6/23" + +#: ../../community/contributors.md +msgid "" +"[c604de0](https://github.com/vllm-project/vllm-" +"ascend/commit/4447e53d7ad5edcda978ca6b0a3a26a73c604de0)" +msgstr "" +"[c604de0](https://github.com/vllm-project/vllm-" +"ascend/commit/4447e53d7ad5edcda978ca6b0a3a26a73c604de0)" + +#: ../../community/contributors.md +msgid "73" +msgstr "73" + +#: ../../community/contributors.md +msgid "[@lyj-jjj](https://github.com/lyj-jjj)" +msgstr "[@lyj-jjj](https://github.com/lyj-jjj)" + +#: ../../community/contributors.md +msgid "" +"[5cbd74e](https://github.com/vllm-project/vllm-" +"ascend/commit/5177bef87a21331dcca11159d3d1438075cbd74e)" +msgstr "" +"[5cbd74e](https://github.com/vllm-project/vllm-" +"ascend/commit/5177bef87a21331dcca11159d3d1438075cbd74e)" + +#: ../../community/contributors.md +msgid "72" +msgstr "72" + +#: ../../community/contributors.md +msgid "[@farawayboat](https://github.com/farawayboat)" +msgstr "[@farawayboat](https://github.com/farawayboat)" + +#: ../../community/contributors.md +msgid "2025/6/21" +msgstr "2025/6/21" + +#: ../../community/contributors.md +msgid "" +"[bc7d392](https://github.com/vllm-project/vllm-" +"ascend/commit/097e7149f75c0806774bc68207f0f6270bc7d392)" +msgstr "" +"[bc7d392](https://github.com/vllm-project/vllm-" +"ascend/commit/097e7149f75c0806774bc68207f0f6270bc7d392)" + +#: ../../community/contributors.md +msgid "71" +msgstr "71" + +#: ../../community/contributors.md +msgid "[@yuancaoyaoHW](https://github.com/yuancaoyaoHW)" +msgstr "[@yuancaoyaoHW](https://github.com/yuancaoyaoHW)" + +#: ../../community/contributors.md +msgid "2025/6/20" +msgstr "2025/6/20" + +#: ../../community/contributors.md +msgid "" +"[7aa0b94](https://github.com/vllm-project/vllm-" +"ascend/commit/00ae250f3ced68317bc91c93dc1f1a0977aa0b94)" +msgstr "" +"[7aa0b94](https://github.com/vllm-project/vllm-" +"ascend/commit/00ae250f3ced68317bc91c93dc1f1a0977aa0b94)" + +#: ../../community/contributors.md +msgid "70" +msgstr "70" + +#: ../../community/contributors.md +msgid "[@songshanhu07](https://github.com/songshanhu07)" +msgstr "[@songshanhu07](https://github.com/songshanhu07)" + +#: ../../community/contributors.md +msgid "2025/6/18" +msgstr "2025/6/18" + +#: ../../community/contributors.md +msgid "" +"[5e1de1f](https://github.com/vllm-project/vllm-" +"ascend/commit/2a70dbbdb8f55002de3313e17dfd595e1de1f)" +msgstr "" +"[5e1de1f](https://github.com/vllm-project/vllm-" +"ascend/commit/2a70dbbdb8f55002de3313e17dfd595e1de1f)" + +#: ../../community/contributors.md +msgid "69" +msgstr "69" + +#: ../../community/contributors.md +msgid "[@wangyanhui-cmss](https://github.com/wangyanhui-cmss)" +msgstr "[@wangyanhui-cmss](https://github.com/wangyanhui-cmss)" + +#: ../../community/contributors.md +msgid "2025/6/12" +msgstr "2025/6/12" + +#: ../../community/contributors.md +msgid "" +"[40c9e88](https://github.com/vllm-project/vllm-" +"ascend/commit/2a5fb4014b863cee6abc3009f5bc5340c9e88)" +msgstr "" +"[40c9e88](https://github.com/vllm-project/vllm-" +"ascend/commit/2a5fb4014b863cee6abc3009f5bc5340c9e88)" + +#: ../../community/contributors.md +msgid "68" +msgstr "68" + +#: ../../community/contributors.md +msgid "[@chenwaner](https://github.com/chenwaner)" +msgstr "[@chenwaner](https://github.com/chenwaner)" + +#: ../../community/contributors.md +msgid "2025/6/11" +msgstr "2025/6/11" + +#: ../../community/contributors.md +msgid "" +"[c696169](https://github.com/vllm-project/vllm-" +"ascend/commit/e46dc142bf1180453c64226d76854fc1ec696169)" +msgstr "" +"[c696169](https://github.com/vllm-project/vllm-" +"ascend/commit/e46dc142bf1180453c64226d76854fc1ec696169)" + +#: ../../community/contributors.md +msgid "67" +msgstr "67" + +#: ../../community/contributors.md +msgid "[@yzim](https://github.com/yzim)" +msgstr "[@yzim](https://github.com/yzim)" + +#: ../../community/contributors.md +msgid "" +"[aaf701b](https://github.com/vllm-project/vllm-" +"ascend/commit/4153a5091b698c2270d160409e7fee73baaf701b)" +msgstr "" +"[aaf701b](https://github.com/vllm-project/vllm-" +"ascend/commit/4153a5091b698c2270d160409e7fee73baaf701b)" + +#: ../../community/contributors.md +msgid "66" +msgstr "66" + +#: ../../community/contributors.md +msgid "[@Yuxiao-Xu](https://github.com/Yuxiao-Xu)" +msgstr "[@Yuxiao-Xu](https://github.com/Yuxiao-Xu)" + +#: ../../community/contributors.md +msgid "2025/6/9" +msgstr "2025/6/9" + +#: ../../community/contributors.md +msgid "" +"[6b853f1](https://github.com/vllm-project/vllm-" +"ascend/commit/6b853f15fe69ba335d2745ebcf14a164d0bcc505)" +msgstr "" +"[6b853f1](https://github.com/vllm-project/vllm-" +"ascend/commit/6b853f15fe69ba335d2745ebcf14a164d0bcc505)" + +#: ../../community/contributors.md +msgid "65" +msgstr "65" + +#: ../../community/contributors.md +msgid "[@ChenTaoyu-SJTU](https://github.com/ChenTaoyu-SJTU)" +msgstr "[@ChenTaoyu-SJTU](https://github.com/ChenTaoyu-SJTU)" + +#: ../../community/contributors.md +msgid "2025/6/7" +msgstr "2025/6/7" + +#: ../../community/contributors.md +msgid "" +"[20dedba](https://github.com/vllm-project/vllm-" +"ascend/commit/20dedba5d1fc84b7ae8b49f9ce3e3649389e2193)" +msgstr "" +"[20dedba](https://github.com/vllm-project/vllm-" +"ascend/commit/20dedba5d1fc84b7ae8b49f9ce3e3649389e2193)" + +#: ../../community/contributors.md +msgid "64" +msgstr "64" + +#: ../../community/contributors.md +msgid "[@zxdukki](https://github.com/zxdukki)" +msgstr "[@zxdukki](https://github.com/zxdukki)" + +#: ../../community/contributors.md +msgid "" +"[87ebaef](https://github.com/vllm-project/vllm-" +"ascend/commit/87ebaef4e4e519988f27a6aa378f614642202ecf)" +msgstr "" +"[87ebaef](https://github.com/vllm-project/vllm-" +"ascend/commit/87ebaef4e4e519988f27a6aa378f614642202ecf)" + +#: ../../community/contributors.md +msgid "63" +msgstr "63" + +#: ../../community/contributors.md +msgid "[@sdmyzlp](https://github.com/sdmyzlp)" +msgstr "[@sdmyzlp](https://github.com/sdmyzlp)" + +#: ../../community/contributors.md +msgid "" +"[3640c60](https://github.com/vllm-project/vllm-" +"ascend/commit/3640c60b0eb4d4cb104e20bfa406d3f1d17920a7)" +msgstr "" +"[3640c60](https://github.com/vllm-project/vllm-" +"ascend/commit/3640c60b0eb4d4cb104e20bfa406d3f1d17920a7)" + +#: ../../community/contributors.md +msgid "62" +msgstr "62" + +#: ../../community/contributors.md +msgid "[@weijinqian0](https://github.com/weijinqian0)" +msgstr "[@weijinqian0](https://github.com/weijinqian0)" + +#: ../../community/contributors.md +msgid "" +"[e9ada68](https://github.com/vllm-project/vllm-" +"ascend/commit/e9ada685ece798f9fe0d4a287e3f5246a8a7207b)" +msgstr "" +"[e9ada68](https://github.com/vllm-project/vllm-" +"ascend/commit/e9ada685ece798f9fe0d4a287e3f5246a8a7207b)" + +#: ../../community/contributors.md +msgid "61" +msgstr "61" + +#: ../../community/contributors.md +msgid "[@hahazhky](https://github.com/hahazhky)" +msgstr "[@hahazhky](https://github.com/hahazhky)" + +#: ../../community/contributors.md +msgid "2025/6/6" +msgstr "2025/6/6" + +#: ../../community/contributors.md +msgid "" +"[0b12c2a](https://github.com/vllm-project/vllm-" +"ascend/commit/0b12c2acf7d9fd192beebebf662298067d9a5435)" +msgstr "" +"[0b12c2a](https://github.com/vllm-project/vllm-" +"ascend/commit/0b12c2acf7d9fd192beebebf662298067d9a5435)" + +#: ../../community/contributors.md +msgid "60" +msgstr "60" + +#: ../../community/contributors.md +msgid "[@depeng1994](https://github.com/depeng1994)" +msgstr "[@depeng1994](https://github.com/depeng1994)" + +#: ../../community/contributors.md +msgid "" +"[6b094a2](https://github.com/vllm-project/vllm-" +"ascend/commit/6b094a2bd49a8a41eb3647568b2d9e5b337db81f)" +msgstr "" +"[6b094a2](https://github.com/vllm-project/vllm-" +"ascend/commit/6b094a2bd49a8a41eb3647568b2d9e5b337db81f)" + +#: ../../community/contributors.md +msgid "59" +msgstr "59" + +#: ../../community/contributors.md +msgid "[@David9857](https://github.com/David9857)" +msgstr "[@David9857](https://github.com/David9857)" + +#: ../../community/contributors.md +msgid "2025/6/5" +msgstr "2025/6/5" + +#: ../../community/contributors.md +msgid "" +"[78431b3](https://github.com/vllm-project/vllm-" +"ascend/commit/78431b34694dfa3c8f54ed7cc626660318557927)" +msgstr "" +"[78431b3](https://github.com/vllm-project/vllm-" +"ascend/commit/78431b34694dfa3c8f54ed7cc626660318557927)" + +#: ../../community/contributors.md +msgid "58" +msgstr "58" + +#: ../../community/contributors.md +msgid "[@momo609](https://github.com/momo609)" +msgstr "[@momo609](https://github.com/momo609)" + +#: ../../community/contributors.md +msgid "" +"[908a851](https://github.com/vllm-project/vllm-" +"ascend/commit/908a851a776cfd9051cc062119e6ec481561c6f7)" +msgstr "" +"[908a851](https://github.com/vllm-project/vllm-" +"ascend/commit/908a851a776cfd9051cc062119e6ec481561c6f7)" + +#: ../../community/contributors.md +msgid "57" +msgstr "57" + +#: ../../community/contributors.md +msgid "[@zhangxinyuehfad](https://github.com/zhangxinyuehfad)" +msgstr "[@zhangxinyuehfad](https://github.com/zhangxinyuehfad)" + +#: ../../community/contributors.md +msgid "" +"[7737aaa](https://github.com/vllm-project/vllm-" +"ascend/commit/7737aaa40f699b233a35fb61e908b687adc1e2e5)" +msgstr "" +"[7737aaa](https://github.com/vllm-project/vllm-" +"ascend/commit/7737aaa40f699b233a35fb61e908b687adc1e2e5)" + +#: ../../community/contributors.md +msgid "56" +msgstr "56" + +#: ../../community/contributors.md +msgid "[@NINGBENZHE](https://github.com/NINGBENZHE)" +msgstr "[@NINGBENZHE](https://github.com/NINGBENZHE)" + +#: ../../community/contributors.md +msgid "2025/6/3" +msgstr "2025/6/3" + +#: ../../community/contributors.md +msgid "" +"[6ec64a3](https://github.com/vllm-project/vllm-" +"ascend/commit/6ec64a3f9686df65b5a23a41aa301e669db19099)" +msgstr "" +"[6ec64a3](https://github.com/vllm-project/vllm-" +"ascend/commit/6ec64a3f9686df65b5a23a41aa301e669db19099)" + +#: ../../community/contributors.md +msgid "55" +msgstr "55" + +#: ../../community/contributors.md +msgid "[@XWFAlone](https://github.com/XWFAlone)" +msgstr "[@XWFAlone](https://github.com/XWFAlone)" + +#: ../../community/contributors.md +msgid "2025/5/30" +msgstr "2025/5/30" + +#: ../../community/contributors.md +msgid "" +"[3442fbd](https://github.com/vllm-project/vllm-" +"ascend/commit/3442fbdb235b4c6d72c2bc64a49707a7bd89958e)" +msgstr "" +"[3442fbd](https://github.com/vllm-project/vllm-" +"ascend/commit/3442fbdb235b4c6d72c2bc64a49707a7bd89958e)" + +#: ../../community/contributors.md +msgid "54" +msgstr "54" + +#: ../../community/contributors.md +msgid "[@YisongJiang](https://github.com/YisongJiang)" +msgstr "[@YisongJiang](https://github.com/YisongJiang)" + +#: ../../community/contributors.md +msgid "2025/5/29" +msgstr "2025/5/29" + +#: ../../community/contributors.md +msgid "" +"[90afaf6](https://github.com/vllm-project/vllm-" +"ascend/commit/90afaf6306f680307462becf3c78585737579851)" +msgstr "" +"[90afaf6](https://github.com/vllm-project/vllm-" +"ascend/commit/90afaf6306f680307462becf3c78585737579851)" + +#: ../../community/contributors.md +msgid "53" +msgstr "53" + +#: ../../community/contributors.md +msgid "[@ponix-j](https://github.com/ponix-j)" +msgstr "[@ponix-j](https://github.com/ponix-j)" + +#: ../../community/contributors.md +msgid "2025/5/23" +msgstr "2025/5/23" + +#: ../../community/contributors.md +msgid "" +"[df58fb8](https://github.com/vllm-project/vllm-" +"ascend/commit/df58fb80eee24139fc61c495be3ce79cf81b3f73)" +msgstr "" +"[df58fb8](https://github.com/vllm-project/vllm-" +"ascend/commit/df58fb80eee24139fc61c495be3ce79cf81b3f73)" + +#: ../../community/contributors.md +msgid "52" +msgstr "52" + +#: ../../community/contributors.md +msgid "[@ttanzhiqiang](https://github.com/ttanzhiqiang)" +msgstr "[@ttanzhiqiang](https://github.com/ttanzhiqiang)" + +#: ../../community/contributors.md +msgid "" +"[dc6172e](https://github.com/vllm-project/vllm-" +"ascend/commit/dc6172efd3860ce95b40a7b3e93611f875f06d40)" +msgstr "" +"[dc6172e](https://github.com/vllm-project/vllm-" +"ascend/commit/dc6172efd3860ce95b40a7b3e93611f875f06d40)" + +#: ../../community/contributors.md +msgid "51" +msgstr "51" + +#: ../../community/contributors.md +msgid "[@yangpuPKU](https://github.com/yangpuPKU)" +msgstr "[@yangpuPKU](https://github.com/yangpuPKU)" + +#: ../../community/contributors.md +msgid "" +"[46df67a](https://github.com/vllm-project/vllm-" +"ascend/commit/46df67a5e9ab73fade08cbb2d8c0155cee7316d1)" +msgstr "" +"[46df67a](https://github.com/vllm-project/vllm-" +"ascend/commit/46df67a5e9ab73fade08cbb2d8c0155cee7316d1)" + +#: ../../community/contributors.md +msgid "50" +msgstr "50" + +#: ../../community/contributors.md +msgid "[@wonderful199082](https://github.com/wonderful199082)" +msgstr "[@wonderful199082](https://github.com/wonderful199082)" + +#: ../../community/contributors.md +msgid "2025/5/20" +msgstr "2025/5/20" + +#: ../../community/contributors.md +msgid "" +"[5cf9ff1](https://github.com/vllm-project/vllm-" +"ascend/commit/5cf9ff18e91b0b7031c258d71a257b8e24689763)" +msgstr "" +"[5cf9ff1](https://github.com/vllm-project/vllm-" +"ascend/commit/5cf9ff18e91b0b7031c258d71a257b8e24689763)" + +#: ../../community/contributors.md +msgid "49" +msgstr "49" + +#: ../../community/contributors.md +msgid "[@22dimensions](https://github.com/22dimensions)" +msgstr "[@22dimensions](https://github.com/22dimensions)" + +#: ../../community/contributors.md +msgid "2025/5/17" +msgstr "2025/5/17" + +#: ../../community/contributors.md +msgid "" +"[a8730e7](https://github.com/vllm-project/vllm-" +"ascend/commit/a8730e7a3c4ac6c4b39a5946c943252fdea6cce5)" +msgstr "" +"[a8730e7](https://github.com/vllm-project/vllm-" +"ascend/commit/a8730e7a3c4ac6c4b39a5946c943252fdea6cce5)" + +#: ../../community/contributors.md +msgid "48" +msgstr "48" + +#: ../../community/contributors.md +msgid "[@cxcxflying](https://github.com/cxcxflying)" +msgstr "[@cxcxflying](https://github.com/cxcxflying)" + +#: ../../community/contributors.md +msgid "2025/5/13" +msgstr "2025/5/13" + +#: ../../community/contributors.md +msgid "" +"[e564470](https://github.com/vllm-project/vllm-" +"ascend/commit/e56447033889ca95df512208cab22ef832bfdf07)" +msgstr "" +"[e564470](https://github.com/vllm-project/vllm-" +"ascend/commit/e56447033889ca95df512208cab22ef832bfdf07)" + +#: ../../community/contributors.md +msgid "47" +msgstr "47" + +#: ../../community/contributors.md +msgid "[@NeverRaR](https://github.com/NeverRaR)" +msgstr "[@NeverRaR](https://github.com/NeverRaR)" + +#: ../../community/contributors.md +msgid "2025/5/12" +msgstr "2025/5/12" + +#: ../../community/contributors.md +msgid "" +"[efabd72](https://github.com/vllm-project/vllm-" +"ascend/commit/efabd722eb757e49aa309c173bbec91ca8c4ced1)" +msgstr "" +"[efabd72](https://github.com/vllm-project/vllm-" +"ascend/commit/efabd722eb757e49aa309c173bbec91ca8c4ced1)" + +#: ../../community/contributors.md +msgid "46" +msgstr "46" + +#: ../../community/contributors.md +msgid "[@chris668899](https://github.com/chris668899)" +msgstr "[@chris668899](https://github.com/chris668899)" + +#: ../../community/contributors.md +msgid "2025/5/8" +msgstr "2025/5/8" + +#: ../../community/contributors.md +msgid "" +"[6c02088](https://github.com/vllm-project/vllm-" +"ascend/commit/6c020883a8332b5c519f4f6502733edd9b391c2b)" +msgstr "" +"[6c02088](https://github.com/vllm-project/vllm-" +"ascend/commit/6c020883a8332b5c519f4f6502733edd9b391c2b)" + +#: ../../community/contributors.md +msgid "45" +msgstr "45" + +#: ../../community/contributors.md +msgid "[@sunbaosong](https://github.com/sunbaosong)" +msgstr "[@sunbaosong](https://github.com/sunbaosong)" + +#: ../../community/contributors.md +msgid "2025/5/6" +msgstr "2025/5/6" + +#: ../../community/contributors.md +msgid "" +"[d6bfae8](https://github.com/vllm-project/vllm-" +"ascend/commit/d6bfae8eeebedf677b643b712d367a3a69c9cce4)" +msgstr "" +"[d6bfae8](https://github.com/vllm-project/vllm-" +"ascend/commit/d6bfae8eeebedf677b643b712d367a3a69c9cce4)" + +#: ../../community/contributors.md +msgid "44" +msgstr "44" + +#: ../../community/contributors.md +msgid "[@ApsarasX](https://github.com/ApsarasX)" +msgstr "[@ApsarasX](https://github.com/ApsarasX)" + +#: ../../community/contributors.md +msgid "2025/4/29" +msgstr "2025/4/29" + +#: ../../community/contributors.md +msgid "" +"[87975fa](https://github.com/vllm-project/vllm-" +"ascend/commit/87975fa058fe3f90d204ded42a08989a8dcb413e)" +msgstr "" +"[87975fa](https://github.com/vllm-project/vllm-" +"ascend/commit/87975fa058fe3f90d204ded42a08989a8dcb413e)" + +#: ../../community/contributors.md +msgid "43" +msgstr "43" + +#: ../../community/contributors.md +msgid "[@zouyida2052](https://github.com/zouyida2052)" +msgstr "[@zouyida2052](https://github.com/zouyida2052)" + +#: ../../community/contributors.md +msgid "2025/4/28" +msgstr "2025/4/28" + +#: ../../community/contributors.md +msgid "" +"[b9528e6](https://github.com/vllm-project/vllm-" +"ascend/commit/b9528e6ecdc417cf444e55a0ce4a2bafdef0ea3b)" +msgstr "" +"[b9528e6](https://github.com/vllm-project/vllm-" +"ascend/commit/b9528e6ecdc417cf444e55a0ce4a2bafdef0ea3b)" + +#: ../../community/contributors.md +msgid "42" +msgstr "42" + +#: ../../community/contributors.md +msgid "[@ZhengJun9](https://github.com/ZhengJun9)" +msgstr "[@ZhengJun9](https://github.com/ZhengJun9)" + +#: ../../community/contributors.md +msgid "" +"[1791113](https://github.com/vllm-project/vllm-" +"ascend/commit/17911138c90d78a76bd691e9dcb56763db35b19f)" +msgstr "" +"[1791113](https://github.com/vllm-project/vllm-" +"ascend/commit/17911138c90d78a76bd691e9dcb56763db35b19f)" + +#: ../../community/contributors.md +msgid "41" +msgstr "41" + +#: ../../community/contributors.md +msgid "[@linfeng-yuan](https://github.com/linfeng-yuan)" +msgstr "[@linfeng-yuan](https://github.com/linfeng-yuan)" + +#: ../../community/contributors.md +msgid "" +"[2204e4d](https://github.com/vllm-project/vllm-" +"ascend/commit/2204e4d08f8e10cf9c30154a14eaa5ca956c2acd)" +msgstr "" +"[2204e4d](https://github.com/vllm-project/vllm-" +"ascend/commit/2204e4d08f8e10cf9c30154a14eaa5ca956c2acd)" + +#: ../../community/contributors.md +msgid "40" +msgstr "40" + +#: ../../community/contributors.md +msgid "2025/4/27" +msgstr "2025/4/27" + +#: ../../community/contributors.md +msgid "" +"[fa4a5d9](https://github.com/vllm-project/vllm-" +"ascend/commit/fa4a5d980e8845a88b9162cf169f0a5ab230f8a5)" +msgstr "" +"[fa4a5d9](https://github.com/vllm-project/vllm-" +"ascend/commit/fa4a5d980e8845a88b9162cf169f0a5ab230f8a5)" + +#: ../../community/contributors.md +msgid "39" +msgstr "39" + +#: ../../community/contributors.md +msgid "[@fakeYan](https://github.com/fakeYan)" +msgstr "[@fakeYan](https://github.com/fakeYan)" + +#: ../../community/contributors.md +msgid "2025/4/23" +msgstr "2025/4/23" + +#: ../../community/contributors.md +msgid "" +"[05bdcbe](https://github.com/vllm-project/vllm-" +"ascend/commit/05bdcbeae47c7fcb9b1c30cad059abf1d40b5421)" +msgstr "" +"[05bdcbe](https://github.com/vllm-project/vllm-" +"ascend/commit/05bdcbeae47c7fcb9b1c30cad059abf1d40b5421)" + +#: ../../community/contributors.md +msgid "38" +msgstr "38" + +#: ../../community/contributors.md +msgid "[@RongRongStudio](https://github.com/RongRongStudio)" +msgstr "[@RongRongStudio](https://github.com/RongRongStudio)" + +#: ../../community/contributors.md +msgid "2025/4/22" +msgstr "2025/4/22" + +#: ../../community/contributors.md +msgid "" +"[848e041](https://github.com/vllm-project/vllm-" +"ascend/commit/848e041a54732c923660dd02daf8e9bf439736a2)" +msgstr "" +"[848e041](https://github.com/vllm-project/vllm-" +"ascend/commit/848e041a54732c923660dd02daf8e9bf439736a2)" + +#: ../../community/contributors.md +msgid "37" +msgstr "37" + +#: ../../community/contributors.md +msgid "[@paulyu12](https://github.com/paulyu12)" +msgstr "[@paulyu12](https://github.com/paulyu12)" + +#: ../../community/contributors.md +msgid "2025/4/17" +msgstr "2025/4/17" + +#: ../../community/contributors.md +msgid "" +"[697908f](https://github.com/vllm-project/vllm-" +"ascend/commit/697908f5cd7c65a3a917ec1a962b0886efc98c7e)" +msgstr "" +"[697908f](https://github.com/vllm-project/vllm-" +"ascend/commit/697908f5cd7c65a3a917ec1a962b0886efc98c7e)" + +#: ../../community/contributors.md +msgid "36" +msgstr "36" + +#: ../../community/contributors.md +msgid "[@heartStrive1998](https://github.com/heartStrive1998)" +msgstr "[@heartStrive1998](https://github.com/heartStrive1998)" + +#: ../../community/contributors.md +msgid "2025/4/16" +msgstr "2025/4/16" + +#: ../../community/contributors.md +msgid "" +"[2f15503](https://github.com/vllm-project/vllm-" +"ascend/commit/2f155039dc3997640854daef469bbf0cb77dc6ed)" +msgstr "" +"[2f15503](https://github.com/vllm-project/vllm-" +"ascend/commit/2f155039dc3997640854daef469bbf0cb77dc6ed)" + +#: ../../community/contributors.md +msgid "35" +msgstr "35" + +#: ../../community/contributors.md +msgid "[@eeethenQ](https://github.com/eeethenQ)" +msgstr "[@eeethenQ](https://github.com/eeethenQ)" + +#: ../../community/contributors.md +msgid "2025/4/15" +msgstr "2025/4/15" + +#: ../../community/contributors.md +msgid "" +"[44a8301](https://github.com/vllm-project/vllm-" +"ascend/commit/44a8301424ded94dae83e13b837f5bfc0a1bfc15)" +msgstr "" +"[44a8301](https://github.com/vllm-project/vllm-" +"ascend/commit/44a8301424ded94dae83e13b837f5bfc0a1bfc15)" + +#: ../../community/contributors.md +msgid "34" +msgstr "34" + +#: ../../community/contributors.md +msgid "[@wxsIcey](https://github.com/wxsIcey)" +msgstr "[@wxsIcey](https://github.com/wxsIcey)" + +#: ../../community/contributors.md +msgid "2025/4/10" +msgstr "2025/4/10" + +#: ../../community/contributors.md +msgid "" +"[d05ea17](https://github.com/vllm-project/vllm-" +"ascend/commit/d05ea17427b82a506b97409a7de8359f18f565f7)" +msgstr "" +"[d05ea17](https://github.com/vllm-project/vllm-" +"ascend/commit/d05ea17427b82a506b97409a7de8359f18f565f7)" + +#: ../../community/contributors.md +msgid "33" +msgstr "33" + +#: ../../community/contributors.md +msgid "[@yx0716](https://github.com/yx0716)" +msgstr "[@yx0716](https://github.com/yx0716)" + +#: ../../community/contributors.md +msgid "2025/4/8" +msgstr "2025/4/8" + +#: ../../community/contributors.md +msgid "" +"[5d62393](https://github.com/vllm-project/vllm-" +"ascend/commit/5d6239306be9b0f5ac6dbaa137048c372a92ff20)" +msgstr "" +"[5d62393](https://github.com/vllm-project/vllm-" +"ascend/commit/5d6239306be9b0f5ac6dbaa137048c372a92ff20)" + +#: ../../community/contributors.md +msgid "32" +msgstr "32" + +#: ../../community/contributors.md +msgid "[@celestialli](https://github.com/celestialli)" +msgstr "[@celestialli](https://github.com/celestialli)" + +#: ../../community/contributors.md +msgid "2025/4/7" +msgstr "2025/4/7" + +#: ../../community/contributors.md +msgid "" +"[2b765dc](https://github.com/vllm-project/vllm-" +"ascend/commit/2b765dcc4974b1bafc26ff5da817ce7e652f0eb0)" +msgstr "" +"[2b765dc](https://github.com/vllm-project/vllm-" +"ascend/commit/2b765dcc4974b1bafc26ff5da817ce7e652f0eb0)" + +#: ../../community/contributors.md +msgid "31" +msgstr "31" + +#: ../../community/contributors.md +msgid "[@hfadzxy](https://github.com/hfadzxy)" +msgstr "[@hfadzxy](https://github.com/hfadzxy)" + +#: ../../community/contributors.md +msgid "2025/3/30" +msgstr "2025/3/30" + +#: ../../community/contributors.md +msgid "" +"[7beb433](https://github.com/vllm-project/vllm-" +"ascend/commit/7beb4339dc8047af9ef64db1d0a8c59ddbb3709f)" +msgstr "" +"[7beb433](https://github.com/vllm-project/vllm-" +"ascend/commit/7beb4339dc8047af9ef64db1d0a8c59ddbb3709f)" + +#: ../../community/contributors.md +msgid "30" +msgstr "30" + +#: ../../community/contributors.md +msgid "[@wuhuikx](https://github.com/wuhuikx)" +msgstr "[@wuhuikx](https://github.com/wuhuikx)" + +#: ../../community/contributors.md +msgid "2025/3/28" +msgstr "2025/3/28" + +#: ../../community/contributors.md +msgid "" +"[57a84bb](https://github.com/vllm-project/vllm-" +"ascend/commit/57a84bb7befeaa0dc62aa35fa406e4d6affbfcca)" +msgstr "" +"[57a84bb](https://github.com/vllm-project/vllm-" +"ascend/commit/57a84bb7befeaa0dc62aa35fa406e4d6affbfcca)" + +#: ../../community/contributors.md +msgid "29" +msgstr "29" + +#: ../../community/contributors.md +msgid "[@zzzzwwjj](https://github.com/zzzzwwjj)" +msgstr "[@zzzzwwjj](https://github.com/zzzzwwjj)" + +#: ../../community/contributors.md +msgid "" +"[12390af](https://github.com/vllm-project/vllm-" +"ascend/commit/12390af075962456ecc8233d8dcce7064b75f390)" +msgstr "" +"[12390af](https://github.com/vllm-project/vllm-" +"ascend/commit/12390af075962456ecc8233d8dcce7064b75f390)" + +#: ../../community/contributors.md +msgid "28" +msgstr "28" + +#: ../../community/contributors.md +msgid "" +"[27e86b9](https://github.com/vllm-project/vllm-" +"ascend/commit/27e86b993a6a810d818143ec9dbfc439a419fa77)" +msgstr "" +"[27e86b9](https://github.com/vllm-project/vllm-" +"ascend/commit/27e86b993a6a810d818143ec9dbfc439a419fa77)" + +#: ../../community/contributors.md +msgid "27" +msgstr "27" + +#: ../../community/contributors.md +msgid "[@ZhengZhenyu](https://github.com/ZhengZhenyu)" +msgstr "[@ZhengZhenyu](https://github.com/ZhengZhenyu)" + +#: ../../community/contributors.md +msgid "2025/3/26" +msgstr "2025/3/26" + +#: ../../community/contributors.md +msgid "" +"[0b5a964](https://github.com/vllm-project/vllm-" +"ascend/commit/0b5a9643fd6c3240d7ede669e37209d7ff433841)" +msgstr "" +"[0b5a964](https://github.com/vllm-project/vllm-" +"ascend/commit/0b5a9643fd6c3240d7ede669e37209d7ff433841)" + +#: ../../community/contributors.md +msgid "26" +msgstr "26" + +#: ../../community/contributors.md +msgid "[@baifanxxx](https://github.com/baifanxxx)" +msgstr "[@baifanxxx](https://github.com/baifanxxx)" + +#: ../../community/contributors.md +msgid "" +"[1225052](https://github.com/vllm-project/vllm-" +"ascend/commit/122505208ff6284f409846ca7294f4a4b9883285)" +msgstr "" +"[1225052](https://github.com/vllm-project/vllm-" +"ascend/commit/122505208ff6284f409846ca7294f4a4b9883285)" + +#: ../../community/contributors.md +msgid "25" +msgstr "25" + +#: ../../community/contributors.md +msgid "[@rjg-lyh](https://github.com/rjg-lyh)" +msgstr "[@rjg-lyh](https://github.com/rjg-lyh)" + +#: ../../community/contributors.md +msgid "2025/3/13" +msgstr "2025/3/13" + +#: ../../community/contributors.md +msgid "" +"[6512470](https://github.com/vllm-project/vllm-" +"ascend/commit/65124705fb39d4cc2c94c80254421e067a82fe50)" +msgstr "" +"[6512470](https://github.com/vllm-project/vllm-" +"ascend/commit/65124705fb39d4cc2c94c80254421e067a82fe50)" + +#: ../../community/contributors.md +msgid "24" +msgstr "24" + +#: ../../community/contributors.md +msgid "[@xiemingda-1002](https://github.com/xiemingda-1002)" +msgstr "[@xiemingda-1002](https://github.com/xiemingda-1002)" + +#: ../../community/contributors.md +msgid "2025/3/12" +msgstr "2025/3/12" + +#: ../../community/contributors.md +msgid "" +"[59ea23d](https://github.com/vllm-project/vllm-" +"ascend/commit/59ea23d0d394879d7f33de6fd22242539b9c3cc5)" +msgstr "" +"[59ea23d](https://github.com/vllm-project/vllm-" +"ascend/commit/59ea23d0d394879d7f33de6fd22242539b9c3cc5)" + +#: ../../community/contributors.md +msgid "23" +msgstr "23" + +#: ../../community/contributors.md +msgid "[@yiz-liu](https://github.com/yiz-liu)" +msgstr "[@yiz-liu](https://github.com/yiz-liu)" + +#: ../../community/contributors.md +msgid "2025/3/11" +msgstr "2025/3/11" + +#: ../../community/contributors.md +msgid "" +"[0db6670](https://github.com/vllm-project/vllm-" +"ascend/commit/0db6670bfab8cb1d84c9e7270df0a1d42d6ce7ca)" +msgstr "" +"[0db6670](https://github.com/vllm-project/vllm-" +"ascend/commit/0db6670bfab8cb1d84c9e7270df0a1d42d6ce7ca)" + +#: ../../community/contributors.md +msgid "22" +msgstr "22" + +#: ../../community/contributors.md +msgid "[@new-TonyWang](https://github.com/new-TonyWang)" +msgstr "[@new-TonyWang](https://github.com/new-TonyWang)" + +#: ../../community/contributors.md +msgid "" +"[dfb4e23](https://github.com/vllm-project/vllm-" +"ascend/commit/dfb4e23e9d820ac992a071c123bbe983c7b01b2e)" +msgstr "" +"[dfb4e23](https://github.com/vllm-project/vllm-" +"ascend/commit/dfb4e23e9d820ac992a071c123bbe983c7b01b2e)" + +#: ../../community/contributors.md +msgid "21" +msgstr "21" + +#: ../../community/contributors.md +msgid "[@mengwei805](https://github.com/mengwei805)" +msgstr "[@mengwei805](https://github.com/mengwei805)" + +#: ../../community/contributors.md +msgid "2025/3/6" +msgstr "2025/3/6" + +#: ../../community/contributors.md +msgid "" +"[8fcf3d1](https://github.com/vllm-project/vllm-" +"ascend/commit/8fcf3d1704084626db35c5dc82ade446508598d4)" +msgstr "" +"[8fcf3d1](https://github.com/vllm-project/vllm-" +"ascend/commit/8fcf3d1704084626db35c5dc82ade446508598d4)" + +#: ../../community/contributors.md +msgid "20" +msgstr "20" + +#: ../../community/contributors.md +msgid "[@baymax591](https://github.com/baymax591)" +msgstr "[@baymax591](https://github.com/baymax591)" + +#: ../../community/contributors.md +msgid "2025/2/28" +msgstr "2025/2/28" + +#: ../../community/contributors.md +msgid "" +"[e8131b9](https://github.com/vllm-project/vllm-" +"ascend/commit/e8131b99cf199f50a304e6e6fb125a1b95bcc92b)" +msgstr "" +"[e8131b9](https://github.com/vllm-project/vllm-" +"ascend/commit/e8131b99cf199f50a304e6e6fb125a1b95bcc92b)" + +#: ../../community/contributors.md +msgid "19" +msgstr "19" + +#: ../../community/contributors.md +msgid "[@dependabot](https://github.com/dependabot)" +msgstr "[@dependabot](https://github.com/dependabot)" + +#: ../../community/contributors.md +msgid "2025/2/27" +msgstr "2025/2/27" + +#: ../../community/contributors.md +msgid "" +"[a5564ed](https://github.com/vllm-project/vllm-" +"ascend/commit/a5564ed5d8fd9818936a22d9ea35951a27513b4c)" +msgstr "" +"[a5564ed](https://github.com/vllm-project/vllm-" +"ascend/commit/a5564ed5d8fd9818936a22d9ea35951a27513b4c)" + +#: ../../community/contributors.md +msgid "18" +msgstr "18" + +#: ../../community/contributors.md +msgid "[@shink](https://github.com/shink)" +msgstr "[@shink](https://github.com/shink)" + +#: ../../community/contributors.md +msgid "" +"[6aed833](https://github.com/vllm-project/vllm-" +"ascend/commit/6aed83335cbe92fd0b8ef07c28966a753d012ccb)" +msgstr "" +"[6aed833](https://github.com/vllm-project/vllm-" +"ascend/commit/6aed83335cbe92fd0b8ef07c28966a753d012ccb)" + +#: ../../community/contributors.md +msgid "17" +msgstr "17" + +#: ../../community/contributors.md +msgid "[@wwfu109](https://github.com/wwfu109)" +msgstr "[@wwfu109](https://github.com/wwfu109)" + +#: ../../community/contributors.md +msgid "" +"[b074047](https://github.com/vllm-project/vllm-" +"ascend/commit/b07404766bdaf6e3cebc5cb0aba89a247501302e)" +msgstr "" +"[b074047](https://github.com/vllm-project/vllm-" +"ascend/commit/b07404766bdaf6e3cebc5cb0aba89a247501302e)" + +#: ../../community/contributors.md +msgid "16" +msgstr "16" + +#: ../../community/contributors.md +msgid "[@kunpengW-code](https://github.com/kunpengW-code)" +msgstr "[@kunpengW-code](https://github.com/kunpengW-code)" + +#: ../../community/contributors.md +msgid "2025/2/26" +msgstr "2025/2/26" + +#: ../../community/contributors.md +msgid "" +"[ca807ce](https://github.com/vllm-project/vllm-" +"ascend/commit/ca807ce49ed64aa89242f5ae29b9862a77648b45)" +msgstr "" +"[ca807ce](https://github.com/vllm-project/vllm-" +"ascend/commit/ca807ce49ed64aa89242f5ae29b9862a77648b45)" + +#: ../../community/contributors.md +msgid "15" +msgstr "15" + +#: ../../community/contributors.md +msgid "[@Yaphets24](https://github.com/Yaphets24)" +msgstr "[@Yaphets24](https://github.com/Yaphets24)" + +#: ../../community/contributors.md +msgid "2025/2/22" +msgstr "2025/2/22" + +#: ../../community/contributors.md +msgid "" +"[d0b3cb4](https://github.com/vllm-project/vllm-" +"ascend/commit/d0b3cb4fa79d5fc7f8245a3c68885ce1fa030ba4)" +msgstr "" +"[d0b3cb4](https://github.com/vllm-project/vllm-" +"ascend/commit/d0b3cb4fa79d5fc7f8245a3c68885ce1fa030ba4)" + +#: ../../community/contributors.md +msgid "14" +msgstr "14" + +#: ../../community/contributors.md +msgid "[@noemotiovon](https://github.com/noemotiovon)" +msgstr "[@noemotiovon](https://github.com/noemotiovon)" + +#: ../../community/contributors.md +msgid "2025/2/21" +msgstr "2025/2/21" + +#: ../../community/contributors.md +msgid "" +"[202b39a](https://github.com/vllm-project/vllm-" +"ascend/commit/202b39a38c2869b0ecc3df486550fb555a2eb0c0)" +msgstr "" +"[202b39a](https://github.com/vllm-project/vllm-" +"ascend/commit/202b39a38c2869b0ecc3df486550fb555a2eb0c0)" + +#: ../../community/contributors.md +msgid "13" +msgstr "13" + +#: ../../community/contributors.md +msgid "[@SidaoY](https://github.com/SidaoY)" +msgstr "[@SidaoY](https://github.com/SidaoY)" + +#: ../../community/contributors.md +msgid "2025/2/18" +msgstr "2025/2/18" + +#: ../../community/contributors.md +msgid "" +"[718c763](https://github.com/vllm-project/vllm-" +"ascend/commit/718c7638555d12cd43ea2a9e497e185778b68595)" +msgstr "" +"[718c763](https://github.com/vllm-project/vllm-" +"ascend/commit/718c7638555d12cd43ea2a9e497e185778b68595)" + +#: ../../community/contributors.md +msgid "12" +msgstr "12" + +#: ../../community/contributors.md +msgid "[@ShiyaNiu](https://github.com/ShiyaNiu)" +msgstr "[@ShiyaNiu](https://github.com/ShiyaNiu)" + +#: ../../community/contributors.md +msgid "2025/2/17" +msgstr "2025/2/17" + +#: ../../community/contributors.md +msgid "" +"[36ea38f](https://github.com/vllm-project/vllm-" +"ascend/commit/36ea38fde56437ff1745bd95cd8d9e02a6578d38)" +msgstr "" +"[36ea38f](https://github.com/vllm-project/vllm-" +"ascend/commit/36ea38fde56437ff1745bd95cd8d9e02a6578d38)" + +#: ../../community/contributors.md +msgid "11" +msgstr "11" + +#: ../../community/contributors.md +msgid "[@ji-huazhong](https://github.com/ji-huazhong)" +msgstr "[@ji-huazhong](https://github.com/ji-huazhong)" + +#: ../../community/contributors.md +msgid "2025/2/12" +msgstr "2025/2/12" + +#: ../../community/contributors.md +msgid "" +"[c8b57d1](https://github.com/vllm-project/vllm-" +"ascend/commit/c8b57d10b24efcd9b4fadeb66cfbf66aa3dd5f82)" +msgstr "" +"[c8b57d1](https://github.com/vllm-project/vllm-" +"ascend/commit/c8b57d10b24efcd9b4fadeb66cfbf66aa3dd5f82)" + +#: ../../community/contributors.md +msgid "10" +msgstr "10" + +#: ../../community/contributors.md +msgid "[@Angazenn](https://github.com/Angazenn)" +msgstr "[@Angazenn](https://github.com/Angazenn)" + +#: ../../community/contributors.md +msgid "2025/2/11" +msgstr "2025/2/11" + +#: ../../community/contributors.md +msgid "" +"[7637759](https://github.com/vllm-project/vllm-" +"ascend/commit/7637759056028839c74960d9cfd3ce6275ee5d35)" +msgstr "" +"[7637759](https://github.com/vllm-project/vllm-" +"ascend/commit/7637759056028839c74960d9cfd3ce6275ee5d35)" + +#: ../../community/contributors.md +msgid "9" +msgstr "9" + +#: ../../community/contributors.md +msgid "[@whx-sjtu](https://github.com/whx-sjtu)" +msgstr "[@whx-sjtu](https://github.com/whx-sjtu)" + +#: ../../community/contributors.md +msgid "2025/2/7" +msgstr "2025/2/7" + +#: ../../community/contributors.md +msgid "" +"[8fc5dc9](https://github.com/vllm-project/vllm-" +"ascend/commit/8fc5dc966aaf4e174d1ec0d1902c40289411ec0e)" +msgstr "" +"[8fc5dc9](https://github.com/vllm-project/vllm-" +"ascend/commit/8fc5dc966aaf4e174d1ec0d1902c40289411ec0e)" + +#: ../../community/contributors.md +msgid "8" +msgstr "8" + +#: ../../community/contributors.md +msgid "[@zouyida2002](https://github.com/zouyida2002)" +msgstr "[@zouyida2002](https://github.com/zouyida2002)" + +#: ../../community/contributors.md +msgid "" +"[4495fc6](https://github.com/vllm-project/vllm-" +"ascend/commit/4495fc68389e3fb1ef14534c202948931e38446b)" +msgstr "" +"[4495fc6](https://github.com/vllm-project/vllm-" +"ascend/commit/4495fc68389e3fb1ef14534c202948931e38446b)" + +#: ../../community/contributors.md +msgid "7" +msgstr "7" + +#: ../../community/contributors.md +msgid "[@hw_whx](https://github.com/hw_whx)" +msgstr "[@hw_whx](https://github.com/hw_whx)" + +#: ../../community/contributors.md +msgid "" +"[7d16772](https://github.com/vllm-project/vllm-" +"ascend/commit/7d1677263bc6628ade33bb780455e0f6e5b9b27a)" +msgstr "" +"[7d16772](https://github.com/vllm-project/vllm-" +"ascend/commit/7d1677263bc6628ade33bb780455e0f6e5b9b27a)" + +#: ../../community/contributors.md +msgid "6" +msgstr "6" + +#: ../../community/contributors.md +msgid "[@MengqingCao](https://github.com/MengqingCao)" +msgstr "[@MengqingCao](https://github.com/MengqingCao)" + +#: ../../community/contributors.md +msgid "2025/2/6" +msgstr "2025/2/6" + +#: ../../community/contributors.md +msgid "" +"[7d9ae22](https://github.com/vllm-project/vllm-" +"ascend/commit/7d9ae22ecb6dc3ea4e720e5109cf46e1ae7da730)" +msgstr "" +"[7d9ae22](https://github.com/vllm-project/vllm-" +"ascend/commit/7d9ae22ecb6dc3ea4e720e5109cf46e1ae7da730)" + +#: ../../community/contributors.md +msgid "5" +msgstr "5" + +#: ../../community/contributors.md +msgid "[@Potabk](https://github.com/Potabk)" +msgstr "[@Potabk](https://github.com/Potabk)" + +#: ../../community/contributors.md +msgid "" +"[8cb5615](https://github.com/vllm-project/vllm-" +"ascend/commit/8cb5615fb010b34c2f4f89e03e6257bfee851f86)" +msgstr "" +"[8cb5615](https://github.com/vllm-project/vllm-" +"ascend/commit/8cb5615fb010b34c2f4f89e03e6257bfee851f86)" + +#: ../../community/contributors.md +msgid "4" +msgstr "4" + +#: ../../community/contributors.md +msgid "" +"[a48b9ad](https://github.com/vllm-project/vllm-" +"ascend/commit/a48b9addefd292af523644411d4ff4142dd4bc66)" +msgstr "" +"[a48b9ad](https://github.com/vllm-project/vllm-" +"ascend/commit/a48b9addefd292af523644411d4ff4142dd4bc66)" + +#: ../../community/contributors.md +msgid "3" +msgstr "3" + +#: ../../community/contributors.md +msgid "[@shen-shanshan](https://github.com/shen-shanshan)" +msgstr "[@shen-shanshan](https://github.com/shen-shanshan)" + +#: ../../community/contributors.md +msgid "" +"[bfccf73](https://github.com/vllm-project/vllm-" +"ascend/commit/bfccf739e2fe121b54d9b198c2ec205a9379190e)" +msgstr "" +"[bfccf73](https://github.com/vllm-project/vllm-" +"ascend/commit/bfccf739e2fe121b54d9b198c2ec205a9379190e)" + +#: ../../community/contributors.md +msgid "2" +msgstr "2" + +#: ../../community/contributors.md +msgid "2025/2/5" +msgstr "2025/2/5" + +#: ../../community/contributors.md +msgid "" +"[d5e7756](https://github.com/vllm-project/vllm-" +"ascend/commit/d5e7756028bd5884ade96b654555c375770a2f64)" +msgstr "" +"[d5e7756](https://github.com/vllm-project/vllm-" +"ascend/commit/d5e7756028bd5884ade96b654555c375770a2f64)" + +#: ../../community/contributors.md +msgid "1" +msgstr "1" + +#: ../../community/contributors.md +msgid "[@simon-mo](https://github.com/simon-mo)" +msgstr "[@simon-mo](https://github.com/simon-mo)" + +#: ../../community/contributors.md +msgid "2025/1/29" +msgstr "2025/1/29" + +#: ../../community/contributors.md +msgid "" +"[eb28342](https://github.com/vllm-project/vllm-" +"ascend/commit/eb283428ddc17207b6866118f9bc15454b5b8801)" +msgstr "" +"[eb28342](https://github.com/vllm-project/vllm-" +"ascend/commit/eb283428ddc17207b6866118f9bc15454b5b8801)" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/community/governance.po b/docs/source/locale/zh_CN/LC_MESSAGES/community/governance.po new file mode 100644 index 000000000..030aa24b0 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/community/governance.po @@ -0,0 +1,204 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../community/governance.md:1 +msgid "Governance" +msgstr "治理" + +#: ../../community/governance.md:3 +msgid "Mission" +msgstr "使命" + +#: ../../community/governance.md:4 +msgid "" +"As a vital component of vLLM, the vLLM Ascend project is dedicated to " +"providing an easy, fast, and cheap LLM Serving for Everyone on Ascend NPU, " +"and to actively contribute to the enrichment of vLLM." +msgstr "" +"作为 vLLM 的重要组成部分，vLLM Ascend 项目致力于为所有人在 Ascend NPU 上提供简单、快速且低成本的大语言模型服务，并积极促进" +" vLLM 的丰富发展。" + +#: ../../community/governance.md:6 +msgid "Principles" +msgstr "原则" + +#: ../../community/governance.md:7 +msgid "" +"vLLM Ascend follows the vLLM community's code of conduct：[vLLM - CODE OF " +"CONDUCT](https://github.com/vllm-project/vllm/blob/main/CODE_OF_CONDUCT.md)" +msgstr "" +"vLLM Ascend 遵循 vLLM 社区的行为准则：[vLLM - 行为准则](https://github.com/vllm-" +"project/vllm/blob/main/CODE_OF_CONDUCT.md)" + +#: ../../community/governance.md:9 +msgid "Governance - Mechanics" +msgstr "治理 - 机制" + +#: ../../community/governance.md:10 +msgid "" +"vLLM Ascend is an open-source project under the vLLM community, where the " +"authority to appoint roles is ultimately determined by the vLLM community. " +"It adopts a hierarchical technical governance structure." +msgstr "vLLM Ascend 是 vLLM 社区下的一个开源项目，其角色任命权最终由 vLLM 社区决定。它采用分层的技术治理结构。" + +#: ../../community/governance.md:12 +msgid "Contributor:" +msgstr "贡献者：" + +#: ../../community/governance.md:14 +msgid "" +"**Responsibility:** Help new contributors on boarding, handle and respond to" +" community questions, review RFCs, code" +msgstr "**职责：** 帮助新贡献者加入，处理和回复社区问题，审查RFC和代码" + +#: ../../community/governance.md:16 +msgid "" +"**Requirements:** Complete at least 1 contribution. Contributor is someone " +"who consistently and actively participates in a project, included but not " +"limited to issue/review/commits/community involvement." +msgstr "**要求：** 完成至少1次贡献。贡献者是指持续且积极参与项目的人，包括但不限于问题、评审、提交和社区参与。" + +#: ../../community/governance.md:18 +msgid "" +"Contributors will be empowered [vllm-project/vllm-" +"ascend](https://github.com/vllm-project/vllm-ascend) Github repo `Triage` " +"permissions (`Can read and clone this repository. Can also manage issues and" +" pull requests`) to help community developers collaborate more efficiently." +msgstr "" +"贡献者将被赋予 [vllm-project/vllm-ascend](https://github.com/vllm-project/vllm-" +"ascend) Github 仓库的 `Triage` 权限（`可读取和克隆此仓库。还可以管理问题和拉取请求`），以帮助社区开发者更加高效地协作。" + +#: ../../community/governance.md:20 +msgid "Maintainer:" +msgstr "维护者：" + +#: ../../community/governance.md:22 +msgid "" +"**Responsibility:** Develop the project's vision and mission. Maintainers " +"are responsible for driving the technical direction of the entire project " +"and ensuring its overall success, possessing code merge permissions. They " +"formulate the roadmap, review contributions from community members, " +"continuously contribute code, and actively engage in community activities " +"(such as regular meetings/events)." +msgstr "" +"**责任：** " +"制定项目的愿景和使命。维护者负责引领整个项目的技术方向并确保其整体成功，拥有代码合并权限。他们制定路线图，审核社区成员的贡献，持续贡献代码，并积极参与社区活动（如定期会议/活动）。" + +#: ../../community/governance.md:24 +msgid "" +"**Requirements:** Deep understanding of ‌vLLM‌ and ‌vLLM Ascend‌ codebases, " +"with a commitment to sustained code contributions. Competency in " +"‌design/development/PR review workflows‌." +msgstr "" +"**要求：** 深入理解 ‌vLLM‌ 和 ‌vLLM Ascend‌ 代码库，并承诺持续贡献代码。具备 ‌设计/开发/PR 审核流程‌ 的能力。" + +#: ../../community/governance.md:25 +msgid "" +"**Review Quality‌:** Actively participate in community code reviews, " +"ensuring high-quality code integration." +msgstr "**评审质量：** 积极参与社区代码评审，确保高质量的代码集成。" + +#: ../../community/governance.md:26 +msgid "" +"**Quality Contribution‌:** Successfully develop and deliver at least one " +"major feature while maintaining consistent high-quality contributions." +msgstr "**质量贡献‌：** 成功开发并交付至少一个主要功能，同时持续保持高质量的贡献。" + +#: ../../community/governance.md:27 +msgid "" +"**Community Involvement‌:** Actively address issues, respond to forum " +"inquiries, participate in discussions, and engage in community-driven tasks." +msgstr "**社区参与：** 积极解决问题，回复论坛询问，参与讨论，并参与社区驱动的任务。" + +#: ../../community/governance.md:29 +msgid "" +"Requires approval from existing Maintainers. The vLLM community has the " +"final decision-making authority." +msgstr "需要现有维护者的批准。vLLM社区拥有最终决策权。" + +#: ../../community/governance.md:31 +msgid "" +"Maintainer will be empowered [vllm-project/vllm-" +"ascend](https://github.com/vllm-project/vllm-ascend) Github repo write " +"permissions (`Can read, clone, and push to this repository. Can also manage " +"issues and pull requests`)." +msgstr "" +"维护者将被授予 [vllm-project/vllm-ascend](https://github.com/vllm-project/vllm-" +"ascend) Github 仓库的写入权限（`可以读取、克隆和推送到此仓库。还可以管理问题和拉取请求`）。" + +#: ../../community/governance.md:33 +msgid "Nominating and Removing Maintainers" +msgstr "提名和移除维护者" + +#: ../../community/governance.md:35 +msgid "The Principles" +msgstr "原则" + +#: ../../community/governance.md:37 +msgid "" +"Membership in vLLM Ascend is given to individuals on merit basis after they " +"demonstrated strong expertise of the vLLM / vLLM Ascend through " +"contributions, reviews and discussions." +msgstr "" +"vLLM Ascend 的成员资格是基于个人能力授予的，只有在通过贡献、评审和讨论展示出对 vLLM / vLLM Ascend " +"的深厚专业知识后，才可获得。" + +#: ../../community/governance.md:39 +msgid "" +"For membership in the maintainer group the individual has to demonstrate " +"strong and continued alignment with the overall vLLM / vLLM Ascend " +"principles." +msgstr "要成为维护者组成员，个人必须表现出与 vLLM / vLLM Ascend 总体原则的高度一致并持续支持。" + +#: ../../community/governance.md:41 +msgid "" +"Light criteria of moving module maintenance to ‘emeritus’ status if they " +"don’t actively participate over long periods of time." +msgstr "如果模块维护人员在长时间内没有积极参与，可根据较宽松的标准将其维护状态转为“荣誉”状态。" + +#: ../../community/governance.md:43 +msgid "The membership is for an individual, not a company." +msgstr "该会员资格属于个人，而非公司。" + +#: ../../community/governance.md:45 +msgid "Nomination and Removal" +msgstr "提名与罢免" + +#: ../../community/governance.md:47 +msgid "" +"Nomination: Anyone can nominate someone to become a maintainer (include " +"self-nominate). All existing maintainers are responsible for evaluating the " +"nomination. The nominator should provide nominee's info around the strength " +"of the candidate to be a maintainer, include but not limited to review " +"quality, quality contribution, community involvement." +msgstr "" +"提名：任何人都可以提名他人成为维护者（包括自荐）。所有现有维护者都有责任评估提名。提名人应提供被提名人成为维护者的相关优势信息，包括但不限于评审质量、优质贡献、社区参与等。" + +#: ../../community/governance.md:48 +msgid "" +"Removal: Anyone can nominate a person to be removed from maintainer position" +" (include self-nominate). All existing maintainers are responsible for " +"evaluating the nomination. The nominator should provide nominee's info, " +"include but not limited to lack of activity, conflict with the overall " +"direction and other information that makes them unfit to be a maintainer." +msgstr "" +"移除：任何人都可以提名某人被移出维护者职位（包括自荐）。所有现有维护者都有责任评估该提名。提名者应提供被提名人的相关信息，包括但不限于缺乏活动、与整体方向冲突以及使其不适合作为维护者的其他信息。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/index.po new file mode 100644 index 000000000..3d91ba728 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/index.po @@ -0,0 +1,103 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../community/user_stories/index.md:15 +msgid "More details" +msgstr "更多细节" + +#: ../../community/user_stories/index.md:1 +msgid "User Stories" +msgstr "用户故事" + +#: ../../community/user_stories/index.md:3 +msgid "" +"Read case studies on how users and developers solves real, everyday problems" +" with vLLM Ascend" +msgstr "阅读案例研究，了解用户和开发者如何使用 vLLM Ascend 解决实际日常问题。" + +#: ../../community/user_stories/index.md:5 +msgid "" +"[LLaMA-Factory](./llamafactory.md) is an easy-to-use and efficient platform " +"for training and fine-tuning large language models, it supports vLLM Ascend " +"to speed up inference since [LLaMA-" +"Factory#7739](https://github.com/hiyouga/LLaMA-Factory/pull/7739), gain 2x " +"performance enhancement of inference." +msgstr "" +"[LLaMA-Factory](./llamafactory.md) 是一个易于使用且高效的大语言模型训练与微调平台，自 [LLaMA-" +"Factory#7739](https://github.com/hiyouga/LLaMA-Factory/pull/7739) 起支持 vLLM " +"Ascend 加速推理，推理性能提升 2 倍。" + +#: ../../community/user_stories/index.md:7 +msgid "" +"[Huggingface/trl](https://github.com/huggingface/trl) is a cutting-edge " +"library designed for post-training foundation models using advanced " +"techniques like SFT, PPO and DPO, it uses vLLM Ascend since " +"[v0.17.0](https://github.com/huggingface/trl/releases/tag/v0.17.0) to " +"support RLHF on Ascend NPU." +msgstr "" +"[Huggingface/trl](https://github.com/huggingface/trl) 是一个前沿的库，专为使用 SFT、PPO 和" +" DPO 等先进技术对基础模型进行后训练而设计。从 " +"[v0.17.0](https://github.com/huggingface/trl/releases/tag/v0.17.0) 版本开始，该库利用" +" vLLM Ascend 来支持在 Ascend NPU 上进行 RLHF。" + +#: ../../community/user_stories/index.md:9 +msgid "" +"[MindIE Turbo](https://pypi.org/project/mindie-turbo) is an LLM inference " +"engine acceleration plug-in library developed by Huawei on Ascend hardware, " +"which includes self-developed large language model optimization algorithms " +"and optimizations related to the inference engine framework. It supports " +"vLLM Ascend since " +"[2.0rc1](https://www.hiascend.com/document/detail/zh/mindie/20RC1/AcceleratePlugin/turbodev/mindie-" +"turbo-0001.html)." +msgstr "" +"[MindIE Turbo](https://pypi.org/project/mindie-turbo) " +"是华为在昇腾硬件上开发的一款用于加速LLM推理引擎的插件库，包含自主研发的大语言模型优化算法及与推理引擎框架相关的优化。从 " +"[2.0rc1](https://www.hiascend.com/document/detail/zh/mindie/20RC1/AcceleratePlugin/turbodev/mindie-" +"turbo-0001.html) 起，支持 vLLM Ascend。" + +#: ../../community/user_stories/index.md:11 +msgid "" +"[GPUStack](https://github.com/gpustack/gpustack) is an open-source GPU " +"cluster manager for running AI models. It supports vLLM Ascend since " +"[v0.6.2](https://github.com/gpustack/gpustack/releases/tag/v0.6.2), see more" +" GPUStack performance evaluation info on " +"[link](https://mp.weixin.qq.com/s/pkytJVjcH9_OnffnsFGaew)." +msgstr "" +"[GPUStack](https://github.com/gpustack/gpustack) 是一个开源的 GPU 集群管理器，用于运行 AI " +"模型。从 [v0.6.2](https://github.com/gpustack/gpustack/releases/tag/v0.6.2) " +"版本开始支持 vLLM Ascend，更多 GPUStack 性能评测信息见 " +"[链接](https://mp.weixin.qq.com/s/pkytJVjcH9_OnffnsFGaew)。" + +#: ../../community/user_stories/index.md:13 +msgid "" +"[verl](https://github.com/volcengine/verl) is a flexible, efficient and " +"production-ready RL training library for large language models (LLMs), uses " +"vLLM Ascend since " +"[v0.4.0](https://github.com/volcengine/verl/releases/tag/v0.4.0), see more " +"info on [verl x Ascend " +"Quickstart](https://verl.readthedocs.io/en/latest/ascend_tutorial/ascend_quick_start.html)." +msgstr "" +"[verl](https://github.com/volcengine/verl) " +"是一个灵活、高效且可用于生产环境的大型语言模型（LLM）强化学习训练库，自 " +"[v0.4.0](https://github.com/volcengine/verl/releases/tag/v0.4.0) 起支持 vLLM " +"Ascend，更多信息请参见 [verl x Ascend " +"快速上手](https://verl.readthedocs.io/en/latest/ascend_tutorial/ascend_quick_start.html)。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/llamafactory.po b/docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/llamafactory.po new file mode 100644 index 000000000..4e8c7718d --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/llamafactory.po @@ -0,0 +1,87 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../community/user_stories/llamafactory.md:1 +msgid "LLaMA-Factory" +msgstr "LLaMA-Factory" + +#: ../../community/user_stories/llamafactory.md:3 +msgid "**About / Introduction**" +msgstr "**关于 / 介绍**" + +#: ../../community/user_stories/llamafactory.md:5 +msgid "" +"[LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) is an easy-to-use " +"and efficient platform for training and fine-tuning large language models. " +"With LLaMA-Factory, you can fine-tune hundreds of pre-trained models locally" +" without writing any code." +msgstr "" +"[LLaMA-Factory](https://github.com/hiyouga/LLaMA-Factory) " +"是一个易于使用且高效的平台，用于训练和微调大型语言模型。有了 LLaMA-Factory，你可以在本地对数百个预训练模型进行微调，无需编写任何代码。" + +#: ../../community/user_stories/llamafactory.md:7 +msgid "" +"LLaMA-Facotory users need to evaluate and inference the model after fine-" +"tuning the model." +msgstr "LLaMA-Facotory 用户需要在对模型进行微调后对模型进行评估和推理。" + +#: ../../community/user_stories/llamafactory.md:9 +msgid "**The Business Challenge**" +msgstr "**业务挑战**" + +#: ../../community/user_stories/llamafactory.md:11 +msgid "" +"LLaMA-Factory used transformers to perform inference on Ascend NPU, but the " +"speed was slow." +msgstr "LLaMA-Factory 使用 transformers 在 Ascend NPU 上进行推理，但速度较慢。" + +#: ../../community/user_stories/llamafactory.md:13 +msgid "**Solving Challenges and Benefits with vLLM Ascend**" +msgstr "**通过 vLLM Ascend 解决挑战与收益**" + +#: ../../community/user_stories/llamafactory.md:15 +msgid "" +"With the joint efforts of LLaMA-Factory and vLLM Ascend ([LLaMA-" +"Factory#7739](https://github.com/hiyouga/LLaMA-Factory/pull/7739)), the " +"performance of LLaMA-Factory in the model inference stage has been " +"significantly improved. According to the test results, the inference speed " +"of LLaMA-Factory has been increased to 2x compared to the transformers " +"version." +msgstr "" +"在 LLaMA-Factory 和 vLLM Ascend 的共同努力下（参见 [LLaMA-" +"Factory#7739](https://github.com/hiyouga/LLaMA-Factory/pull/7739)），LLaMA-" +"Factory 在模型推理阶段的性能得到了显著提升。根据测试结果，LLaMA-Factory 的推理速度相比 transformers 版本提升到了 2" +" 倍。" + +#: ../../community/user_stories/llamafactory.md:17 +msgid "**Learn more**" +msgstr "**了解更多**" + +#: ../../community/user_stories/llamafactory.md:19 +msgid "" +"See more about LLaMA-Factory and how it uses vLLM Ascend for inference on " +"the Ascend NPU in the following documentation: [LLaMA-Factory Ascend NPU " +"Inference](https://llamafactory.readthedocs.io/en/latest/advanced/npu_inference.html)." +msgstr "" +"在以下文档中查看更多关于 LLaMA-Factory 以及其如何在 Ascend NPU 上使用 vLLM Ascend 进行推理的信息：[LLaMA-" +"Factory Ascend NPU " +"推理](https://llamafactory.readthedocs.io/en/latest/advanced/npu_inference.html)。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/community/versioning_policy.po b/docs/source/locale/zh_CN/LC_MESSAGES/community/versioning_policy.po new file mode 100644 index 000000000..62b2a480f --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/community/versioning_policy.po @@ -0,0 +1,624 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../community/versioning_policy.md:1 +msgid "Versioning policy" +msgstr "版本管理策略" + +#: ../../community/versioning_policy.md:3 +msgid "" +"Starting with vLLM 0.7.x, the vLLM Ascend Plugin ([vllm-project/vllm-" +"ascend](https://github.com/vllm-project/vllm-ascend)) project follows the " +"[PEP 440](https://peps.python.org/pep-0440/) to publish matching with vLLM " +"([vllm-project/vllm](https://github.com/vllm-project/vllm))." +msgstr "" +"从 vLLM 0.7.x 开始，vLLM Ascend 插件（[vllm-project/vllm-" +"ascend](https://github.com/vllm-project/vllm-ascend)）项目遵循 [PEP " +"440](https://peps.python.org/pep-0440/) ，以与 vLLM（[vllm-" +"project/vllm](https://github.com/vllm-project/vllm)）版本匹配发布。" + +#: ../../community/versioning_policy.md:5 +msgid "vLLM Ascend Plugin versions" +msgstr "vLLM Ascend 插件版本" + +#: ../../community/versioning_policy.md:7 +msgid "" +"Each vLLM Ascend release will be versioned: " +"`v[major].[minor].[micro][rcN][.postN]` (such as `v0.7.3rc1`, `v0.7.3`, " +"`v0.7.3.post1`)" +msgstr "" +"每个 vLLM Ascend 版本将采用以下版本格式：`v[major].[minor].[micro][rcN][.postN]`（例如 " +"`v0.7.3rc1`、`v0.7.3`、`v0.7.3.post1`）" + +#: ../../community/versioning_policy.md:10 +msgid "" +"**Final releases**: will typically be released every **3 months**, will take" +" the vLLM upstream release plan and Ascend software product release plan " +"into comprehensive consideration." +msgstr "**正式版本**：通常每**3个月**发布一次，将综合考虑 vLLM 上游发行计划和昇腾软件产品发行计划。" + +#: ../../community/versioning_policy.md:11 +msgid "" +"**Pre releases**: will typically be released **on demand**, ending with rcN," +" represents the Nth release candidate version, to support early testing by " +"our users prior to a final release." +msgstr "**预发布版本**：通常会**按需发布**，以 rcN 结尾，表示第N个候选发布版本，旨在支持用户在正式发布前进行早期测试。" + +#: ../../community/versioning_policy.md:12 +msgid "" +"**Post releases**: will typically be released **on demand** to support to " +"address minor errors in a final release. It's different from [PEP-440 post " +"release note](https://peps.python.org/pep-0440/#post-releases) suggestion, " +"it will contain actual bug fixes considering that the final release version " +"should be matched strictly with the vLLM final release version " +"(`v[major].[minor].[micro]`). The post version has to be published as a " +"patch version of the final release." +msgstr "" +"**后续版本**：通常会根据需要发布，以支持解决正式发布中的小错误。这与 [PEP-440 " +"的后续版本说明](https://peps.python.org/pep-0440/#post-releases) 建议不同，它将包含实际的 bug " +"修复，因为最终发布版本应严格与 vLLM " +"的最终发布版本（`v[major].[minor].[micro]`）匹配。后续版本必须以正式发布的补丁版本形式发布。" + +#: ../../community/versioning_policy.md:14 +msgid "For example:" +msgstr "例如：" + +#: ../../community/versioning_policy.md:15 +msgid "" +"`v0.7.x`: it's the first final release to match the vLLM `v0.7.x` version." +msgstr "`v0.7.x`：这是第一个与 vLLM `v0.7.x` 版本相匹配的正式发布版本。" + +#: ../../community/versioning_policy.md:16 +msgid "`v0.7.3rc1`: will be the first pre version of vLLM Ascend." +msgstr "`v0.7.3rc1`：将会是 vLLM Ascend 的第一个预发布版本。" + +#: ../../community/versioning_policy.md:17 +msgid "" +"`v0.7.3.post1`: will be the post release if the `v0.7.3` release has some " +"minor errors." +msgstr "`v0.7.3.post1`：如果 `v0.7.3` 版本发布有一些小错误，将作为后续修正版发布。" + +#: ../../community/versioning_policy.md:19 +msgid "Release Compatibility Matrix" +msgstr "版本兼容性矩阵" + +#: ../../community/versioning_policy.md:21 +msgid "Following is the Release Compatibility Matrix for vLLM Ascend Plugin:" +msgstr "以下是 vLLM Ascend 插件的版本兼容性矩阵：" + +#: ../../community/versioning_policy.md +msgid "vLLM Ascend" +msgstr "vLLM Ascend" + +#: ../../community/versioning_policy.md +msgid "vLLM" +msgstr "vLLM" + +#: ../../community/versioning_policy.md +msgid "Python" +msgstr "Python" + +#: ../../community/versioning_policy.md +msgid "Stable CANN" +msgstr "Stable CANN" + +#: ../../community/versioning_policy.md +msgid "PyTorch/torch_npu" +msgstr "PyTorch/torch_npu" + +#: ../../community/versioning_policy.md +msgid "MindIE Turbo" +msgstr "MindIE Turbo" + +#: ../../community/versioning_policy.md +msgid "v0.9.2rc1" +msgstr "v0.9.2rc1" + +#: ../../community/versioning_policy.md +msgid "v0.9.2" +msgstr "v0.9.2" + +#: ../../community/versioning_policy.md +msgid ">= 3.9, < 3.12" +msgstr ">= 3.9，< 3.12" + +#: ../../community/versioning_policy.md +msgid "8.1.RC1" +msgstr "8.1.RC1" + +#: ../../community/versioning_policy.md +msgid "2.5.1 / 2.5.1.post1.dev20250619" +msgstr "2.5.1 / 2.5.1.post1.dev20250619" + +#: ../../community/versioning_policy.md +msgid "v0.9.1rc1" +msgstr "v0.9.1rc1" + +#: ../../community/versioning_policy.md +msgid "v0.9.1" +msgstr "v0.9.1" + +#: ../../community/versioning_policy.md +msgid "2.5.1 / 2.5.1.post1.dev20250528" +msgstr "2.5.1 / 2.5.1.post1.dev20250528" + +#: ../../community/versioning_policy.md +msgid "v0.9.0rc2" +msgstr "v0.9.0rc2" + +#: ../../community/versioning_policy.md +msgid "v0.9.0" +msgstr "v0.9.0" + +#: ../../community/versioning_policy.md +msgid "2.5.1 / 2.5.1" +msgstr "2.5.1 / 2.5.1" + +#: ../../community/versioning_policy.md +msgid "v0.9.0rc1" +msgstr "v0.9.0rc1" + +#: ../../community/versioning_policy.md +msgid "v0.8.5rc1" +msgstr "v0.8.5rc1" + +#: ../../community/versioning_policy.md +msgid "v0.8.5.post1" +msgstr "v0.8.5.post1" + +#: ../../community/versioning_policy.md +msgid "v0.8.4rc2" +msgstr "v0.8.4rc2" + +#: ../../community/versioning_policy.md +msgid "v0.8.4" +msgstr "v0.8.4" + +#: ../../community/versioning_policy.md +msgid "8.0.0" +msgstr "8.0.0" + +#: ../../community/versioning_policy.md +msgid "v0.7.3.post1" +msgstr "v0.7.3.post1" + +#: ../../community/versioning_policy.md +msgid "v0.7.3" +msgstr "v0.7.3" + +#: ../../community/versioning_policy.md +msgid "2.0rc1" +msgstr "2.0候选版本1" + +#: ../../community/versioning_policy.md:34 +msgid "Release cadence" +msgstr "发布节奏" + +#: ../../community/versioning_policy.md:36 +msgid "release window" +msgstr "发布窗口" + +#: ../../community/versioning_policy.md +msgid "Date" +msgstr "日期" + +#: ../../community/versioning_policy.md +msgid "Event" +msgstr "事件" + +#: ../../community/versioning_policy.md +msgid "2025.07.11" +msgstr "2025.07.11" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.9.2rc1" +msgstr "候选发布版本，v0.9.2rc1" + +#: ../../community/versioning_policy.md +msgid "2025.06.22" +msgstr "2025.06.22" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.9.1rc1" +msgstr "候选发布版本，v0.9.1rc1" + +#: ../../community/versioning_policy.md +msgid "2025.06.10" +msgstr "2025.06.10" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.9.0rc2" +msgstr "候选发布版本，v0.9.0rc2" + +#: ../../community/versioning_policy.md +msgid "2025.06.09" +msgstr "2025.06.09" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.9.0rc1" +msgstr "候选发布版本本，v0.9.0rc1" + +#: ../../community/versioning_policy.md +msgid "2025.05.29" +msgstr "2025.05.29" + +#: ../../community/versioning_policy.md +msgid "v0.7.x post release, v0.7.3.post1" +msgstr "v0.7.x 补丁版，v0.7.3.post1" + +#: ../../community/versioning_policy.md +msgid "2025.05.08" +msgstr "2025.05.08" + +#: ../../community/versioning_policy.md +msgid "v0.7.x Final release, v0.7.3" +msgstr "v0.7.x 正式版，v0.7.3" + +#: ../../community/versioning_policy.md +msgid "2025.05.06" +msgstr "2025.05.06" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.8.5rc1" +msgstr "候选发布版本，v0.8.5rc1" + +#: ../../community/versioning_policy.md +msgid "2025.04.28" +msgstr "2025.04.28" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.8.4rc2" +msgstr "候选发布版本，v0.8.4rc2" + +#: ../../community/versioning_policy.md +msgid "2025.04.18" +msgstr "2025.04.18" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.8.4rc1" +msgstr "候选发布版本，v0.8.4rc1" + +#: ../../community/versioning_policy.md +msgid "2025.03.28" +msgstr "2025.03.28" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.7.3rc2" +msgstr "候选发布版本，v0.7.3rc2" + +#: ../../community/versioning_policy.md +msgid "2025.03.14" +msgstr "2025.03.14" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.7.3rc1" +msgstr "候选发布版本，v0.7.3rc1" + +#: ../../community/versioning_policy.md +msgid "2025.02.19" +msgstr "2025.02.19" + +#: ../../community/versioning_policy.md +msgid "Release candidates, v0.7.1rc1" +msgstr "候选发布版本，v0.7.1rc1" + +#: ../../community/versioning_policy.md:53 +msgid "Branch policy" +msgstr "分支策略" + +#: ../../community/versioning_policy.md:55 +msgid "vLLM Ascend has main branch and dev branch." +msgstr "vLLM Ascend 有主分支和开发分支。" + +#: ../../community/versioning_policy.md:57 +msgid "" +"**main**: main branch，corresponds to the vLLM main branch and latest 1 or 2 " +"release version. It is continuously monitored for quality through Ascend CI." +msgstr "**main**：main 分支，对应 vLLM 的主分支和最新的 1 或 2 个发布版本。该分支通过 Ascend CI 持续监控质量。" + +#: ../../community/versioning_policy.md:58 +msgid "" +"**vX.Y.Z-dev**: development branch, created with part of new releases of " +"vLLM. For example, `v0.7.3-dev` is the dev branch for vLLM `v0.7.3` version." +msgstr "" +"**vX.Y.Z-dev**：开发分支，是随着 vLLM 新版本的一部分一起创建的。例如，`v0.7.3-dev` 是 vLLM `v0.7.3` " +"版本的开发分支。" + +#: ../../community/versioning_policy.md:60 +msgid "" +"Usually, a commit should be ONLY first merged in the main branch, and then " +"backported to the dev branch to reduce maintenance costs as much as " +"possible." +msgstr "通常，提交应该只先合并到主分支，然后再回溯合并到开发分支，以尽可能降低维护成本。" + +#: ../../community/versioning_policy.md:62 +msgid "Maintenance branch and EOL:" +msgstr "维护分支与生命周期结束（EOL）：" + +#: ../../community/versioning_policy.md:63 +msgid "The branch status will be in one of the following states:" +msgstr "分支状态将处于以下几种状态之一：" + +#: ../../community/versioning_policy.md +msgid "Branch" +msgstr "分支" + +#: ../../community/versioning_policy.md +msgid "Time frame" +msgstr "时间范围" + +#: ../../community/versioning_policy.md +msgid "Summary" +msgstr "摘要" + +#: ../../community/versioning_policy.md +msgid "Maintained" +msgstr "维护中" + +#: ../../community/versioning_policy.md +msgid "Approximately 2-3 minor versions" +msgstr "大约 2-3 个小版本" + +#: ../../community/versioning_policy.md +msgid "All bugfixes are appropriate. Releases produced, CI commitment." +msgstr "所有的错误修复都是合适的。正常发布版本，持续集成承诺。" + +#: ../../community/versioning_policy.md +msgid "Unmaintained" +msgstr "无人维护" + +#: ../../community/versioning_policy.md +msgid "Community interest driven" +msgstr "社区兴趣驱动" + +#: ../../community/versioning_policy.md +msgid "All bugfixes are appropriate. No Releases produced, No CI commitment" +msgstr "所有的 bug 修复都是合适的。没有发布版本，不承诺持续集成（CI）。" + +#: ../../community/versioning_policy.md +msgid "End of Life (EOL)" +msgstr "生命周期结束（EOL）" + +#: ../../community/versioning_policy.md +msgid "N/A" +msgstr "不适用" + +#: ../../community/versioning_policy.md +msgid "Branch no longer accepting changes" +msgstr "该分支不再接受更改" + +#: ../../community/versioning_policy.md:71 +msgid "Branch state" +msgstr "分支状态" + +#: ../../community/versioning_policy.md:73 +msgid "" +"Note that vLLM Ascend will only be released for a certain vLLM release " +"version rather than all versions. Hence, You might see only part of versions" +" have dev branches (such as only `0.7.1-dev` / `0.7.3-dev` but no " +"`0.7.2-dev`), this is as expected." +msgstr "" +"请注意，vLLM Ascend 只会针对某些 vLLM 发布版本发布，而不是所有版本。因此，您可能会看到只有部分版本拥有开发分支（例如只有 " +"`0.7.1-dev` / `0.7.3-dev`，而没有 `0.7.2-dev`），这是正常现象。" + +#: ../../community/versioning_policy.md:75 +msgid "" +"Usually, each minor version of vLLM (such as 0.7) will correspond to a vLLM " +"Ascend version branch and support its latest version (for example, we plan " +"to support version 0.7.3) as following shown:" +msgstr "" +"通常，vLLM 的每一个小版本（例如 0.7）都会对应一个 vLLM Ascend 版本分支，并支持其最新版本（例如，我们计划支持 0.7.3 " +"版），如下所示：" + +#: ../../community/versioning_policy.md +msgid "Status" +msgstr "状态" + +#: ../../community/versioning_policy.md +msgid "Note" +msgstr "注释" + +#: ../../community/versioning_policy.md +msgid "main" +msgstr "main" + +#: ../../community/versioning_policy.md +msgid "CI commitment for vLLM main branch and vLLM 0.9.2 branch" +msgstr "vLLM 主分支和 vLLM 0.9.2 分支的 CI 承诺" + +#: ../../community/versioning_policy.md +msgid "v0.9.1-dev" +msgstr "v0.9.1-dev" + +#: ../../community/versioning_policy.md +msgid "CI commitment for vLLM 0.9.1 version" +msgstr "vLLM 0.9.1 版本的 CI 承诺" + +#: ../../community/versioning_policy.md +msgid "v0.7.3-dev" +msgstr "v0.7.3-dev" + +#: ../../community/versioning_policy.md +msgid "CI commitment for vLLM 0.7.3 version" +msgstr "vLLM 0.7.3 版本的 CI 承诺" + +#: ../../community/versioning_policy.md +msgid "v0.7.1-dev" +msgstr "v0.7.1-dev" + +#: ../../community/versioning_policy.md +msgid "Replaced by v0.7.3-dev" +msgstr "已被 v0.7.3-dev 替代" + +#: ../../community/versioning_policy.md:84 +msgid "Backward compatibility" +msgstr "向后兼容性" + +#: ../../community/versioning_policy.md:86 +msgid "" +"For main branch, vLLM Ascend should works with vLLM main branch and latest 1" +" or 2 release version. So to ensure the backward compatibility, we will do " +"the following:" +msgstr "" +"对于主分支，vLLM Ascend 应该与 vLLM 主分支以及最新的 1 或 2 个发布版本兼容。因此，为了确保向后兼容性，我们将执行以下操作：" + +#: ../../community/versioning_policy.md:87 +msgid "" +"Both main branch and target vLLM release is tested by Ascend E2E CI. For " +"example, currently, vLLM main branch and vLLM 0.8.4 are tested now." +msgstr "主分支和目标 vLLM 发行版都经过了 Ascend E2E CI 的测试。例如，目前正在测试 vLLM 主分支和 vLLM 0.8.4。" + +#: ../../community/versioning_policy.md:88 +msgid "" +"For code changes, we will make sure that the changes are compatible with the" +" latest 1 or 2 vLLM release version as well. In this case, vLLM Ascend " +"introduced a version check machinism inner the code. It'll check the version" +" of installed vLLM package first to decide which code logic to use. If users" +" hit the `InvalidVersion` error, it sometimes means that they have installed" +" an dev/editable version of vLLM package. In this case, we provide the env " +"variable `VLLM_VERSION` to let users specify the version of vLLM package to " +"use." +msgstr "" +"对于代码更改，我们也会确保这些更改与最新的 1 或 2 个 vLLM 发行版本兼容。在这种情况下，vLLM Ascend " +"在代码中引入了版本检查机制。它会先检查已安装的 vLLM 包的版本，然后决定使用哪段代码逻辑。如果用户遇到 `InvalidVersion` " +"错误，这有时意味着他们安装了 dev/可编辑版本的 vLLM 包。此时，我们提供了环境变量 `VLLM_VERSION`，让用户可以指定要使用的 " +"vLLM 包版本。" + +#: ../../community/versioning_policy.md:89 +msgid "" +"For documentation changes, we will make sure that the changes are compatible" +" with the latest 1 or 2 vLLM release version as well. Note should be added " +"if there are any breaking changes." +msgstr "对于文档更改，我们会确保这些更改也兼容于最新的1个或2个 vLLM 发布版本。如果有任何重大变更，应添加说明。" + +#: ../../community/versioning_policy.md:91 +msgid "Document Branch Policy" +msgstr "文档分支政策" + +#: ../../community/versioning_policy.md:92 +msgid "" +"To reduce maintenance costs, **all branch documentation content should " +"remain consistent, and version differences can be controlled via variables " +"in [docs/source/conf.py](https://github.com/vllm-project/vllm-" +"ascend/blob/main/docs/source/conf.py)**. While this is not a simple task, it" +" is a principle we should strive to follow." +msgstr "" +"为了减少维护成本，**所有分支的文档内容应保持一致，版本差异可以通过 " +"[docs/source/conf.py](https://github.com/vllm-project/vllm-" +"ascend/blob/main/docs/source/conf.py) 中的变量进行控制**。虽然这并非易事，但这是我们应当努力遵循的原则。" + +#: ../../community/versioning_policy.md +msgid "Version" +msgstr "版本" + +#: ../../community/versioning_policy.md +msgid "Purpose" +msgstr "用途" + +#: ../../community/versioning_policy.md +msgid "Code Branch" +msgstr "代码分支" + +#: ../../community/versioning_policy.md +msgid "latest" +msgstr "最新" + +#: ../../community/versioning_policy.md +msgid "Doc for the latest dev branch" +msgstr "最新开发分支的文档" + +#: ../../community/versioning_policy.md +msgid "vX.Y.Z-dev (Will be `main` after the first final release)" +msgstr "vX.Y.Z-dev（在第一个正式版本发布后将成为 `main`）" + +#: ../../community/versioning_policy.md +msgid "version" +msgstr "版本" + +#: ../../community/versioning_policy.md +msgid "Doc for historical released versions" +msgstr "历史版本文档" + +#: ../../community/versioning_policy.md +msgid "Git tags, like vX.Y.Z[rcN]" +msgstr "Git 标签，如 vX.Y.Z[rcN]" + +#: ../../community/versioning_policy.md +msgid "stable（not yet released）" +msgstr "稳定版（尚未发布）" + +#: ../../community/versioning_policy.md +msgid "Doc for latest final release branch" +msgstr "最新正式发布分支的文档" + +#: ../../community/versioning_policy.md +msgid "Will be `vX.Y.Z-dev` after the first official release" +msgstr "首个正式发布后将会是 `vX.Y.Z-dev`" + +#: ../../community/versioning_policy.md:100 +msgid "As shown above:" +msgstr "如上所示：" + +#: ../../community/versioning_policy.md:102 +msgid "" +"`latest` documentation: Matches the current maintenance branch `vX.Y.Z-dev` " +"(Will be `main` after the first final release). Continuously updated to " +"ensure usability for the latest release." +msgstr "" +"`latest` 文档：匹配当前维护分支 `vX.Y.Z-dev`（在首次正式发布后将为 `main`）。持续更新，以确保适用于最新发布版本。" + +#: ../../community/versioning_policy.md:103 +msgid "" +"`version` documentation: Corresponds to specific released versions (e.g., " +"`v0.7.3`, `v0.7.3rc1`). No further updates after release." +msgstr "`version` 文档：对应特定的已发布版本（例如，`v0.7.3`、`v0.7.3rc1`）。发布后不再进行更新。" + +#: ../../community/versioning_policy.md:104 +msgid "" +"`stable` documentation (**not yet released**): Official release " +"documentation. Updates are allowed in real-time after release, typically " +"based on vX.Y.Z-dev. Once stable documentation is available, non-stable " +"versions should display a header warning: `You are viewing the latest " +"developer preview docs. Click here to view docs for the latest stable " +"release.`." +msgstr "" +"`stable` 文档（**尚未发布**）：官方发布版文档。发布后允许实时更新，通常基于 " +"vX.Y.Z-dev。一旦稳定版文档可用，非稳定版本应显示一个顶部警告：`您正在查看最新的开发预览文档。点击此处查看最新稳定版本文档。`" + +#: ../../community/versioning_policy.md:106 +msgid "Software Dependency Management" +msgstr "软件依赖管理" + +#: ../../community/versioning_policy.md:107 +msgid "" +"`torch-npu`: Ascend Extension for PyTorch (torch-npu) releases a stable " +"version to [PyPi](https://pypi.org/project/torch-npu) every 3 months, a " +"development version (aka the POC version) every month, and a nightly version" +" every day. The PyPi stable version **CAN** be used in vLLM Ascend final " +"version, the monthly dev version **ONLY CANN** be used in vLLM Ascend RC " +"version for rapid iteration, the nightly version **CANNOT** be used in vLLM " +"Ascend any version and branches." +msgstr "" +"`torch-npu`：Ascend Extension for PyTorch（torch-npu）每 3 个月会在 " +"[PyPi](https://pypi.org/project/torch-npu) 上发布一个稳定版本，每个月发布一个开发版本（即 POC " +"版本），每天发布一个 nightly 版本。PyPi 上的稳定版本**可以**用于 vLLM Ascend 的正式版本，月度开发版本**只能**用于 " +"vLLM Ascend 的 RC（候选发布）版本以便快速迭代，nightly 版本**不能**用于 vLLM Ascend 的任何版本和分支。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/index.po new file mode 100644 index 000000000..9e457117a --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/index.po @@ -0,0 +1,187 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/contribution/index.md:107 +msgid "Index" +msgstr "索引" + +#: ../../developer_guide/contribution/index.md:1 +msgid "Contributing" +msgstr "贡献" + +#: ../../developer_guide/contribution/index.md:3 +msgid "Building and testing" +msgstr "构建与测试" + +#: ../../developer_guide/contribution/index.md:4 +msgid "" +"It's recommended to set up a local development environment to build and test" +" before you submit a PR." +msgstr "建议先搭建本地开发环境来进行构建和测试，再提交 PR。" + +#: ../../developer_guide/contribution/index.md:7 +msgid "Setup development environment" +msgstr "搭建开发环境" + +#: ../../developer_guide/contribution/index.md:9 +msgid "" +"Theoretically, the vllm-ascend build is only supported on Linux because " +"`vllm-ascend` dependency `torch_npu` only supports Linux." +msgstr "" +"理论上，vllm-ascend 构建仅支持 Linux，因为 `vllm-ascend` 的依赖项 `torch_npu` 只支持 Linux。" + +#: ../../developer_guide/contribution/index.md:12 +msgid "" +"But you can still set up dev env on Linux/Windows/macOS for linting and " +"basic test as following commands:" +msgstr "但你仍然可以在 Linux/Windows/macOS 上按照以下命令设置开发环境，用于代码规约检查和基本测试：" + +#: ../../developer_guide/contribution/index.md:15 +msgid "Run lint locally" +msgstr "在本地运行 lint" + +#: ../../developer_guide/contribution/index.md:33 +msgid "Run CI locally" +msgstr "本地运行CI" + +#: ../../developer_guide/contribution/index.md:35 +msgid "After complete \"Run lint\" setup, you can run CI locally:" +msgstr "在完成“运行 lint”设置后，你可以在本地运行 CI：" + +#: ../../developer_guide/contribution/index.md:61 +msgid "Submit the commit" +msgstr "提交该提交" + +#: ../../developer_guide/contribution/index.md:68 +msgid "" +"🎉 Congratulations! You have completed the development environment setup." +msgstr "🎉 恭喜！你已经完成了开发环境的搭建。" + +#: ../../developer_guide/contribution/index.md:70 +msgid "Test locally" +msgstr "本地测试" + +#: ../../developer_guide/contribution/index.md:72 +msgid "" +"You can refer to [Testing](./testing.md) doc to help you setup testing " +"environment and running tests locally." +msgstr "你可以参考 [测试](./testing.md) 文档，帮助你搭建测试环境并在本地运行测试。" + +#: ../../developer_guide/contribution/index.md:74 +msgid "DCO and Signed-off-by" +msgstr "DCO 和签名确认" + +#: ../../developer_guide/contribution/index.md:76 +msgid "" +"When contributing changes to this project, you must agree to the DCO. " +"Commits must include a `Signed-off-by:` header which certifies agreement " +"with the terms of the DCO." +msgstr "当为本项目贡献更改时，您必须同意 DCO。提交必须包含 `Signed-off-by:` 头部，以证明您同意 DCO 的条款。" + +#: ../../developer_guide/contribution/index.md:78 +msgid "Using `-s` with `git commit` will automatically add this header." +msgstr "在使用 `git commit` 时加上 `-s` 参数会自动添加这个头部信息。" + +#: ../../developer_guide/contribution/index.md:80 +msgid "PR Title and Classification" +msgstr "PR 标题与分类" + +#: ../../developer_guide/contribution/index.md:82 +msgid "" +"Only specific types of PRs will be reviewed. The PR title is prefixed " +"appropriately to indicate the type of change. Please use one of the " +"following:" +msgstr "只有特定类型的 PR 会被审核。PR 标题应使用合适的前缀以指明更改类型。请使用以下之一：" + +#: ../../developer_guide/contribution/index.md:84 +msgid "`[Attention]` for new features or optimization in attention." +msgstr "`[Attention]` 用于注意力机制中新特性或优化。" + +#: ../../developer_guide/contribution/index.md:85 +msgid "`[Communicator]` for new features or optimization in communicators." +msgstr "`[Communicator]` 适用于通信器中的新特性或优化。" + +#: ../../developer_guide/contribution/index.md:86 +msgid "`[ModelRunner]` for new features or optimization in model runner." +msgstr "`[ModelRunner]` 用于模型运行器中的新功能或优化。" + +#: ../../developer_guide/contribution/index.md:87 +msgid "`[Platform]` for new features or optimization in platform." +msgstr "`[Platform]` 用于平台中新功能或优化。" + +#: ../../developer_guide/contribution/index.md:88 +msgid "`[Worker]` for new features or optimization in worker." +msgstr "`[Worker]` 用于 worker 的新功能或优化。" + +#: ../../developer_guide/contribution/index.md:89 +msgid "" +"`[Core]` for new features or optimization in the core vllm-ascend logic " +"(such as platform, attention, communicators, model runner)" +msgstr "`[Core]` 用于核心 vllm-ascend 逻辑中的新特性或优化（例如平台、注意力机制、通信器、模型运行器）。" + +#: ../../developer_guide/contribution/index.md:90 +msgid "`[Kernel]` changes affecting compute kernels and ops." +msgstr "`[Kernel]` 影响计算内核和操作的更改。" + +#: ../../developer_guide/contribution/index.md:91 +msgid "`[Bugfix]` for bug fixes." +msgstr "`[Bugfix]` 用于表示错误修复。" + +#: ../../developer_guide/contribution/index.md:92 +msgid "`[Doc]` for documentation fixes and improvements." +msgstr "`[Doc]` 用于文档修复和改进。" + +#: ../../developer_guide/contribution/index.md:93 +msgid "`[Test]` for tests (such as unit tests)." +msgstr "`[Test]` 用于测试（如单元测试）。" + +#: ../../developer_guide/contribution/index.md:94 +msgid "`[CI]` for build or continuous integration improvements." +msgstr "`[CI]` 用于构建或持续集成的改进。" + +#: ../../developer_guide/contribution/index.md:95 +msgid "" +"`[Misc]` for PRs that do not fit the above categories. Please use this " +"sparingly." +msgstr "对于不属于上述类别的 PR，请使用 `[Misc]`。请谨慎使用此标签。" + +#: ../../developer_guide/contribution/index.md:98 +msgid "" +"If the PR spans more than one category, please include all relevant " +"prefixes." +msgstr "如果拉取请求（PR）涵盖多个类别，请包含所有相关的前缀。" + +#: ../../developer_guide/contribution/index.md:101 +msgid "Others" +msgstr "其他" + +#: ../../developer_guide/contribution/index.md:103 +msgid "" +"You may find more information about contributing to vLLM Ascend backend " +"plugin on " +"[docs.vllm.ai](https://docs.vllm.ai/en/latest/contributing/overview.html)." +" If you find any problem when contributing, you can feel free to submit a PR" +" to improve the doc to help other developers." +msgstr "" +"你可以在 " +"[docs.vllm.ai](https://docs.vllm.ai/en/latest/contributing/overview.html)" +" 上找到有关为 vLLM Ascend 后端插件做贡献的更多信息。如果你在贡献过程中遇到任何问题，欢迎随时提交 PR 来改进文档，以帮助其他开发者。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po new file mode 100644 index 000000000..8a9ca91a5 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po @@ -0,0 +1,237 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/contribution/testing.md:1 +msgid "Testing" +msgstr "测试" + +#: ../../developer_guide/contribution/testing.md:3 +msgid "" +"This secition explains how to write e2e tests and unit tests to verify the " +"implementation of your feature." +msgstr "本节介绍如何编写端到端测试和单元测试，以验证你的功能实现。" + +#: ../../developer_guide/contribution/testing.md:5 +msgid "Setup test environment" +msgstr "设置测试环境" + +#: ../../developer_guide/contribution/testing.md:7 +msgid "" +"The fastest way to setup test environment is to use the main branch " +"container image:" +msgstr "搭建测试环境最快的方法是使用 main 分支的容器镜像：" + +#: ../../developer_guide/contribution/testing.md +msgid "Local (CPU)" +msgstr "本地（CPU）" + +#: ../../developer_guide/contribution/testing.md:18 +msgid "You can run the unit tests on CPU with the following steps:" +msgstr "你可以按照以下步骤在 CPU 上运行单元测试：" + +#: ../../developer_guide/contribution/testing.md +msgid "Single card" +msgstr "单张卡片" + +#: ../../developer_guide/contribution/testing.md:85 +#: ../../developer_guide/contribution/testing.md:123 +msgid "" +"After starting the container, you should install the required packages:" +msgstr "启动容器后，你应该安装所需的软件包：" + +#: ../../developer_guide/contribution/testing.md +msgid "Multi cards" +msgstr "多卡" + +#: ../../developer_guide/contribution/testing.md:137 +msgid "Running tests" +msgstr "运行测试" + +#: ../../developer_guide/contribution/testing.md:139 +msgid "Unit test" +msgstr "单元测试" + +#: ../../developer_guide/contribution/testing.md:141 +msgid "There are several principles to follow when writing unit tests:" +msgstr "编写单元测试时需要遵循几个原则：" + +#: ../../developer_guide/contribution/testing.md:143 +msgid "" +"The test file path should be consistent with source file and start with " +"`test_` prefix, such as: `vllm_ascend/worker/worker_v1.py` --> " +"`tests/ut/worker/test_worker_v1.py`" +msgstr "" +"测试文件的路径应与源文件保持一致，并以 `test_` 前缀开头，例如：`vllm_ascend/worker/worker_v1.py` --> " +"`tests/ut/worker/test_worker_v1.py`" + +#: ../../developer_guide/contribution/testing.md:144 +msgid "" +"The vLLM Ascend test are using unittest framework, see " +"[here](https://docs.python.org/3/library/unittest.html#module-unittest) to " +"understand how to write unit tests." +msgstr "" +"vLLM Ascend 测试使用 unittest " +"框架，参见[这里](https://docs.python.org/3/library/unittest.html#module-" +"unittest)了解如何编写单元测试。" + +#: ../../developer_guide/contribution/testing.md:145 +msgid "" +"All unit tests can be run on CPU, so you must mock the device-related " +"function to host." +msgstr "所有单元测试都可以在 CPU 上运行，因此你必须将与设备相关的函数模拟为 host。" + +#: ../../developer_guide/contribution/testing.md:146 +msgid "" +"Example: [tests/ut/test_ascend_config.py](https://github.com/vllm-" +"project/vllm-ascend/blob/main/tests/ut/test_ascend_config.py)." +msgstr "" +"示例：[tests/ut/test_ascend_config.py](https://github.com/vllm-project/vllm-" +"ascend/blob/main/tests/ut/test_ascend_config.py)。" + +#: ../../developer_guide/contribution/testing.md:147 +msgid "You can run the unit tests using `pytest`:" +msgstr "你可以使用 `pytest` 运行单元测试：" + +#: ../../developer_guide/contribution/testing.md +msgid "Multi cards test" +msgstr "多卡测试" + +#: ../../developer_guide/contribution/testing.md:192 +msgid "E2E test" +msgstr "端到端测试" + +#: ../../developer_guide/contribution/testing.md:194 +msgid "" +"Although vllm-ascend CI provide [e2e test](https://github.com/vllm-" +"project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_test.yaml) on " +"Ascend CI, you can run it locally." +msgstr "" +"虽然 vllm-ascend CI 在 Ascend CI 上提供了 [端到端测试](https://github.com/vllm-" +"project/vllm-" +"ascend/blob/main/.github/workflows/vllm_ascend_test.yaml)，你也可以在本地运行它。" + +#: ../../developer_guide/contribution/testing.md:204 +msgid "You can't run e2e test on CPU." +msgstr "你无法在 CPU 上运行 e2e 测试。" + +#: ../../developer_guide/contribution/testing.md:240 +msgid "" +"This will reproduce e2e test: " +"[vllm_ascend_test.yaml](https://github.com/vllm-project/vllm-" +"ascend/blob/main/.github/workflows/vllm_ascend_test.yaml)." +msgstr "" +"这将复现端到端测试：[vllm_ascend_test.yaml](https://github.com/vllm-project/vllm-" +"ascend/blob/main/.github/workflows/vllm_ascend_test.yaml)。" + +#: ../../developer_guide/contribution/testing.md:242 +msgid "E2E test example:" +msgstr "E2E 测试示例：" + +#: ../../developer_guide/contribution/testing.md:244 +msgid "" +"Offline test example: " +"[`tests/e2e/singlecard/test_offline_inference.py`](https://github.com/vllm-" +"project/vllm-" +"ascend/blob/main/tests/e2e/singlecard/test_offline_inference.py)" +msgstr "" +"离线测试示例：[`tests/e2e/singlecard/test_offline_inference.py`](https://github.com/vllm-" +"project/vllm-" +"ascend/blob/main/tests/e2e/singlecard/test_offline_inference.py)" + +#: ../../developer_guide/contribution/testing.md:245 +msgid "" +"Online test examples: " +"[`tests/e2e/singlecard/test_prompt_embedding.py`](https://github.com/vllm-" +"project/vllm-ascend/blob/main/tests/e2e/singlecard/test_prompt_embedding.py)" +msgstr "" +"在线测试示例：[`tests/e2e/singlecard/test_prompt_embedding.py`](https://github.com/vllm-" +"project/vllm-ascend/blob/main/tests/e2e/singlecard/test_prompt_embedding.py)" + +#: ../../developer_guide/contribution/testing.md:246 +msgid "" +"Correctness test example: " +"[`tests/e2e/singlecard/test_aclgraph.py`](https://github.com/vllm-" +"project/vllm-ascend/blob/main/tests/e2e/singlecard/test_aclgraph.py)" +msgstr "" +"正确性测试示例：[`tests/e2e/singlecard/test_aclgraph.py`](https://github.com/vllm-" +"project/vllm-ascend/blob/main/tests/e2e/singlecard/test_aclgraph.py)" + +#: ../../developer_guide/contribution/testing.md:247 +msgid "" +"Reduced Layer model test example: [test_torchair_graph_mode.py - " +"DeepSeek-V3-Pruning](https://github.com/vllm-project/vllm-" +"ascend/blob/20767a043cccb3764214930d4695e53941de87ec/tests/e2e/multicard/test_torchair_graph_mode.py#L48)" +msgstr "" +"简化层模型测试示例：[test_torchair_graph_mode.py - " +"DeepSeek-V3-Pruning](https://github.com/vllm-project/vllm-" +"ascend/blob/20767a043cccb3764214930d4695e53941de87ec/tests/e2e/multicard/test_torchair_graph_mode.py#L48)" + +#: ../../developer_guide/contribution/testing.md:249 +msgid "" +"The CI resource is limited, you might need to reduce layer number of the " +"model, below is an example of how to generate a reduced layer model:" +msgstr "CI 资源有限，您可能需要减少模型的层数，下面是一个生成减少层数模型的示例：" + +#: ../../developer_guide/contribution/testing.md:250 +msgid "" +"Fork the original model repo in modelscope, we need all the files in the " +"repo except for weights." +msgstr "在 modelscope 中 fork 原始模型仓库，我们需要仓库中的所有文件，除了权重文件。" + +#: ../../developer_guide/contribution/testing.md:251 +#, python-brace-format +msgid "" +"Set `num_hidden_layers` to the expected number of layers, e.g., " +"`{\"num_hidden_layers\": 2,}`" +msgstr "将 `num_hidden_layers` 设置为期望的层数，例如 `{\"num_hidden_layers\": 2,}`" + +#: ../../developer_guide/contribution/testing.md:252 +msgid "" +"Copy the following python script as `generate_random_weight.py`. Set the " +"relevant parameters `MODEL_LOCAL_PATH`, `DIST_DTYPE` and `DIST_MODEL_PATH` " +"as needed:" +msgstr "" +"将以下 Python 脚本复制为 `generate_random_weight.py`。根据需要设置相关参数 " +"`MODEL_LOCAL_PATH`、`DIST_DTYPE` 和 `DIST_MODEL_PATH`：" + +#: ../../developer_guide/contribution/testing.md:270 +msgid "Run doctest" +msgstr "运行 doctest" + +#: ../../developer_guide/contribution/testing.md:272 +msgid "" +"vllm-ascend provides a `vllm-ascend/tests/e2e/run_doctests.sh` command to " +"run all doctests in the doc files. The doctest is a good way to make sure " +"the docs are up to date and the examples are executable, you can run it " +"locally as follows:" +msgstr "" +"vllm-ascend 提供了一个 `vllm-ascend/tests/e2e/run_doctests.sh` 命令，用于运行文档文件中的所有 " +"doctest。doctest 是确保文档保持最新且示例可执行的好方法，你可以按照以下方式在本地运行它：" + +#: ../../developer_guide/contribution/testing.md:280 +msgid "" +"This will reproduce the same environment as the CI: " +"[vllm_ascend_doctest.yaml](https://github.com/vllm-project/vllm-" +"ascend/blob/main/.github/workflows/vllm_ascend_doctest.yaml)." +msgstr "" +"这将复现与 CI 相同的环境：[vllm_ascend_doctest.yaml](https://github.com/vllm-" +"project/vllm-ascend/blob/main/.github/workflows/vllm_ascend_doctest.yaml)。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/index.po new file mode 100644 index 000000000..180606ebc --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/accuracy_report/index.po @@ -0,0 +1,26 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/evaluation/accuracy_report/index.md:1 +#: ../../developer_guide/evaluation/accuracy_report/index.md:3 +msgid "Accuracy Report" +msgstr "准确性报告" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/index.po new file mode 100644 index 000000000..4ea94e39e --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/index.po @@ -0,0 +1,26 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/evaluation/index.md:1 +#: ../../developer_guide/evaluation/index.md:3 +msgid "Accuracy" +msgstr "准确性" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_evalscope.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_evalscope.po new file mode 100644 index 000000000..60ecb0416 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_evalscope.po @@ -0,0 +1,112 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/evaluation/using_evalscope.md:1 +msgid "Using EvalScope" +msgstr "使用 EvalScope" + +#: ../../developer_guide/evaluation/using_evalscope.md:3 +msgid "" +"This document will guide you have model inference stress testing and " +"accuracy testing using [EvalScope](https://github.com/modelscope/evalscope)." +msgstr "" +"本文档将指导您如何使用 [EvalScope](https://github.com/modelscope/evalscope) " +"进行模型推理压力测试和精度测试。" + +#: ../../developer_guide/evaluation/using_evalscope.md:5 +msgid "1. Online serving" +msgstr "1. 在线服务" + +#: ../../developer_guide/evaluation/using_evalscope.md:7 +msgid "You can run docker container to start the vLLM server on a single NPU:" +msgstr "你可以运行 docker 容器，在单个 NPU 上启动 vLLM 服务器：" + +#: ../../developer_guide/evaluation/using_evalscope.md:34 +msgid "If your service start successfully, you can see the info shown below:" +msgstr "如果你的服务启动成功，你会看到如下所示的信息：" + +#: ../../developer_guide/evaluation/using_evalscope.md:42 +msgid "" +"Once your server is started, you can query the model with input prompts in " +"new terminal:" +msgstr "一旦你的服务器启动后，你可以在新的终端中用输入提示词查询模型：" + +#: ../../developer_guide/evaluation/using_evalscope.md:55 +msgid "2. Install EvalScope using pip" +msgstr "2. 使用 pip 安装 EvalScope" + +#: ../../developer_guide/evaluation/using_evalscope.md:57 +msgid "You can install EvalScope by using:" +msgstr "你可以使用以下方式安装 EvalScope：" + +#: ../../developer_guide/evaluation/using_evalscope.md:65 +msgid "3. Run gsm8k accuracy test using EvalScope" +msgstr "3. 使用 EvalScope 运行 gsm8k 准确率测试" + +#: ../../developer_guide/evaluation/using_evalscope.md:67 +msgid "You can `evalscope eval` run gsm8k accuracy test:" +msgstr "你可以使用 `evalscope eval` 运行 gsm8k 准确率测试：" + +#: ../../developer_guide/evaluation/using_evalscope.md:78 +#: ../../developer_guide/evaluation/using_evalscope.md:114 +msgid "After 1-2 mins, the output is as shown below:" +msgstr "1-2 分钟后，输出如下所示：" + +#: ../../developer_guide/evaluation/using_evalscope.md:88 +msgid "" +"See more detail in: [EvalScope doc - Model API Service " +"Evaluation](https://evalscope.readthedocs.io/en/latest/get_started/basic_usage.html#model-" +"api-service-evaluation)." +msgstr "" +"更多详情请见：[EvalScope 文档 - 模型 API " +"服务评测](https://evalscope.readthedocs.io/en/latest/get_started/basic_usage.html#model-" +"api-service-evaluation)。" + +#: ../../developer_guide/evaluation/using_evalscope.md:90 +msgid "4. Run model inference stress testing using EvalScope" +msgstr "4. 使用 EvalScope 运行模型推理压力测试" + +#: ../../developer_guide/evaluation/using_evalscope.md:92 +msgid "Install EvalScope[perf] using pip" +msgstr "使用 pip 安装 EvalScope[perf]" + +#: ../../developer_guide/evaluation/using_evalscope.md:98 +msgid "Basic usage" +msgstr "基本用法" + +#: ../../developer_guide/evaluation/using_evalscope.md:100 +msgid "You can use `evalscope perf` run perf test:" +msgstr "你可以使用 `evalscope perf` 运行性能测试：" + +#: ../../developer_guide/evaluation/using_evalscope.md:112 +msgid "Output results" +msgstr "输出结果" + +#: ../../developer_guide/evaluation/using_evalscope.md:173 +msgid "" +"See more detail in: [EvalScope doc - Model Inference Stress " +"Testing](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test/quick_start.html#basic-" +"usage)." +msgstr "" +"更多详情见：[EvalScope 文档 - " +"模型推理压力测试](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test/quick_start.html#basic-" +"usage)。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po new file mode 100644 index 000000000..69c52cb0d --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po @@ -0,0 +1,65 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/evaluation/using_lm_eval.md:1 +msgid "Using lm-eval" +msgstr "使用 lm-eval" + +#: ../../developer_guide/evaluation/using_lm_eval.md:2 +msgid "" +"This document will guide you have a accuracy testing using [lm-" +"eval](https://github.com/EleutherAI/lm-evaluation-harness)." +msgstr "" +"本文将指导你如何使用 [lm-eval](https://github.com/EleutherAI/lm-evaluation-harness) " +"进行准确率测试。" + +#: ../../developer_guide/evaluation/using_lm_eval.md:4 +msgid "1. Run docker container" +msgstr "1. 运行 docker 容器" + +#: ../../developer_guide/evaluation/using_lm_eval.md:6 +msgid "You can run docker container on a single NPU:" +msgstr "你可以在单个NPU上运行docker容器：" + +#: ../../developer_guide/evaluation/using_lm_eval.md:33 +msgid "2. Run ceval accuracy test using lm-eval" +msgstr "2. 使用 lm-eval 运行 ceval 准确性测试" + +#: ../../developer_guide/evaluation/using_lm_eval.md:34 +msgid "Install lm-eval in the container." +msgstr "在容器中安装 lm-eval。" + +#: ../../developer_guide/evaluation/using_lm_eval.md:39 +msgid "Run the following command:" +msgstr "运行以下命令：" + +#: ../../developer_guide/evaluation/using_lm_eval.md:50 +msgid "After 1-2 mins, the output is as shown below:" +msgstr "1-2 分钟后，输出如下所示：" + +#: ../../developer_guide/evaluation/using_lm_eval.md:62 +msgid "" +"You can see more usage on [Lm-eval Docs](https://github.com/EleutherAI/lm-" +"evaluation-harness/blob/main/docs/README.md)." +msgstr "" +"你可以在 [Lm-eval 文档](https://github.com/EleutherAI/lm-evaluation-" +"harness/blob/main/docs/README.md) 上查看更多用法。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_opencompass.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_opencompass.po new file mode 100644 index 000000000..41c00d661 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_opencompass.po @@ -0,0 +1,83 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/evaluation/using_opencompass.md:1 +msgid "Using OpenCompass" +msgstr "使用 OpenCompass" + +#: ../../developer_guide/evaluation/using_opencompass.md:2 +msgid "" +"This document will guide you have a accuracy testing using " +"[OpenCompass](https://github.com/open-compass/opencompass)." +msgstr "" +"本文档将指导你如何使用 [OpenCompass](https://github.com/open-compass/opencompass) " +"进行准确率测试。" + +#: ../../developer_guide/evaluation/using_opencompass.md:4 +msgid "1. Online Serving" +msgstr "1. 在线服务" + +#: ../../developer_guide/evaluation/using_opencompass.md:6 +msgid "You can run docker container to start the vLLM server on a single NPU:" +msgstr "你可以运行 docker 容器，在单个 NPU 上启动 vLLM 服务器：" + +#: ../../developer_guide/evaluation/using_opencompass.md:32 +msgid "If your service start successfully, you can see the info shown below:" +msgstr "如果你的服务启动成功，你会看到如下所示的信息：" + +#: ../../developer_guide/evaluation/using_opencompass.md:39 +msgid "" +"Once your server is started, you can query the model with input prompts in " +"new terminal:" +msgstr "一旦你的服务器启动后，你可以在新的终端中用输入提示词查询模型：" + +#: ../../developer_guide/evaluation/using_opencompass.md:51 +msgid "2. Run ceval accuracy test using OpenCompass" +msgstr "2. 使用 OpenCompass 运行 ceval 准确率测试" + +#: ../../developer_guide/evaluation/using_opencompass.md:52 +msgid "" +"Install OpenCompass and configure the environment variables in the " +"container." +msgstr "在容器中安装 OpenCompass 并配置环境变量。" + +#: ../../developer_guide/evaluation/using_opencompass.md:64 +msgid "" +"Add `opencompass/configs/eval_vllm_ascend_demo.py` with the following " +"content:" +msgstr "添加 `opencompass/configs/eval_vllm_ascend_demo.py`，内容如下：" + +#: ../../developer_guide/evaluation/using_opencompass.md:104 +msgid "Run the following command:" +msgstr "运行以下命令：" + +#: ../../developer_guide/evaluation/using_opencompass.md:110 +msgid "After 1-2 mins, the output is as shown below:" +msgstr "1-2 分钟后，输出如下所示：" + +#: ../../developer_guide/evaluation/using_opencompass.md:120 +msgid "" +"You can see more usage on [OpenCompass " +"Docs](https://opencompass.readthedocs.io/en/latest/index.html)." +msgstr "" +"你可以在 [OpenCompass " +"文档](https://opencompass.readthedocs.io/en/latest/index.html) 查看更多用法。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/index.po new file mode 100644 index 000000000..57525a3a9 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/index.po @@ -0,0 +1,33 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/feature_guide/index.md:1 +#: ../../developer_guide/feature_guide/index.md:5 +msgid "Feature Guide" +msgstr "功能指南" + +#: ../../developer_guide/feature_guide/index.md:3 +msgid "" +"This section provides an overview of the features implemented in vLLM " +"Ascend. Developers can refer to this guide to understand how vLLM Ascend " +"works." +msgstr "本节概述了 vLLM Ascend 中实现的功能。开发者可以参考本指南以了解 vLLM Ascend 的工作原理。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/patch.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/patch.po new file mode 100644 index 000000000..1e7daa4cc --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/feature_guide/patch.po @@ -0,0 +1,248 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/feature_guide/patch.md:1 +msgid "Patch in vLLM Ascend" +msgstr "在 vLLM Ascend 中的补丁" + +#: ../../developer_guide/feature_guide/patch.md:3 +msgid "" +"vLLM Ascend is a platform plugin for vLLM. Due to the release cycle of vLLM " +"and vLLM Ascend is different, and the hardware limitation in some case, we " +"need to patch some code in vLLM to make it compatible with vLLM Ascend." +msgstr "" +"vLLM Ascend 是 vLLM 的一个平台插件。由于 vLLM 和 vLLM Ascend " +"的发布周期不同，并且在某些情况下存在硬件限制，我们需要对 vLLM 进行一些代码补丁，以使其能够兼容 vLLM Ascend。" + +#: ../../developer_guide/feature_guide/patch.md:5 +msgid "" +"In vLLM Ascend code, we provide a patch module `vllm_ascend/patch` to " +"address the change for vLLM." +msgstr "在 vLLM Ascend 代码中，我们提供了一个补丁模块 `vllm_ascend/patch` 用于应对 vLLM 的变更。" + +#: ../../developer_guide/feature_guide/patch.md:7 +msgid "Principle" +msgstr "原理" + +#: ../../developer_guide/feature_guide/patch.md:9 +msgid "" +"We should keep in mind that Patch is not the best way to make vLLM Ascend " +"compatible. It's just a temporary solution. The best way is to contribute " +"the change to vLLM to make it compatible with vLLM Ascend originally. In " +"vLLM Ascend, we have the basic principle for Patch strategy:" +msgstr "" +"我们需要记住，Patch 不是让 vLLM 兼容 Ascend 的最佳方式，这只是一个临时的解决方案。最好的方法是将修改贡献到 vLLM 项目中，从而让" +" vLLM 原生支持 Ascend。对于 vLLM Ascend，我们对 Patch 策略有一个基本原则：" + +#: ../../developer_guide/feature_guide/patch.md:11 +msgid "Less is more. Please do not patch unless it's the only way currently." +msgstr "少即是多。请不要打补丁，除非这是目前唯一的方法。" + +#: ../../developer_guide/feature_guide/patch.md:12 +msgid "" +"Once a patch is added, it's required to describe the future plan for " +"removing the patch." +msgstr "一旦补丁被添加，必须说明将来移除该补丁的计划。" + +#: ../../developer_guide/feature_guide/patch.md:13 +msgid "Anytime, clean the patch code is welcome." +msgstr "任何时候，欢迎清理补丁代码。" + +#: ../../developer_guide/feature_guide/patch.md:15 +msgid "How it works" +msgstr "工作原理" + +#: ../../developer_guide/feature_guide/patch.md:17 +msgid "In `vllm_ascend/patch`, you can see the code structure as follows:" +msgstr "在 `vllm_ascend/patch` 目录中，你可以看到如下代码结构：" + +#: ../../developer_guide/feature_guide/patch.md:33 +msgid "" +"**platform**: The patch code in this directory is for patching the code in " +"vLLM main process. It's called by " +"`vllm_ascend/platform::NPUPlatform::pre_register_and_update` very early when" +" vLLM is initialized." +msgstr "" +"**platform**：此目录下的补丁代码用于修补 vLLM 主进程中的代码。当 vLLM 初始化时，会在很早的阶段由 " +"`vllm_ascend/platform::NPUPlatform::pre_register_and_update` 调用。" + +#: ../../developer_guide/feature_guide/patch.md:34 +msgid "" +"For online mode, vLLM process calls the platform patch here " +"`vllm/vllm/engine/arg_utils.py::AsyncEngineArgs.add_cli_args` when parsing " +"the cli args." +msgstr "" +"对于在线模式，vLLM 进程在解析命令行参数时，会在 " +"`vllm/vllm/engine/arg_utils.py::AsyncEngineArgs.add_cli_args` 这里调用平台补丁。" + +#: ../../developer_guide/feature_guide/patch.md:35 +msgid "" +"For offline mode, vLLM process calls the platform patch here " +"`vllm/vllm/engine/arg_utils.py::EngineArgs.create_engine_config` when " +"parsing the input parameters." +msgstr "" +"对于离线模式，vLLM 进程在解析输入参数时，会在此处调用平台补丁 " +"`vllm/vllm/engine/arg_utils.py::EngineArgs.create_engine_config`。" + +#: ../../developer_guide/feature_guide/patch.md:36 +msgid "" +"**worker**: The patch code in this directory is for patching the code in " +"vLLM worker process. It's called by " +"`vllm_ascend/worker/worker_v1::NPUWorker::__init__` when the vLLM worker " +"process is initialized." +msgstr "" +"**worker**：此目录中的补丁代码用于修补 vLLM worker 进程中的代码。在初始化 vLLM worker 进程时，会被 " +"`vllm_ascend/worker/worker_v1::NPUWorker::__init__` 调用。" + +#: ../../developer_guide/feature_guide/patch.md:37 +msgid "" +"For both online and offline mode, vLLM engine core process calls the worker " +"patch here `vllm/vllm/worker/worker_base.py::WorkerWrapperBase.init_worker` " +"when initializing the worker process." +msgstr "" +"无论是在线还是离线模式，vLLM 引擎核心进程在初始化 worker 进程时，都会在这里调用 worker " +"补丁：`vllm/vllm/worker/worker_base.py::WorkerWrapperBase.init_worker`。" + +#: ../../developer_guide/feature_guide/patch.md:39 +msgid "" +"In both **platform** and **worker** folder, there are several patch modules." +" They are used for patching different version of vLLM." +msgstr "在 **platform** 和 **worker** 文件夹中都有一些补丁模块。它们用于修补不同版本的 vLLM。" + +#: ../../developer_guide/feature_guide/patch.md:41 +msgid "" +"`patch_0_9_2`: This module is used for patching vLLM 0.9.2. The version is " +"always the nearest version of vLLM. Once vLLM is released, we will drop this" +" patch module and bump to a new version. For example, `patch_0_9_2` is used " +"for patching vLLM 0.9.2." +msgstr "" +"`patch_0_9_2`：此模块用于修补 vLLM 0.9.2。该版本始终对应于 vLLM 的最近版本。一旦 vLLM " +"发布新版本，我们将移除此补丁模块并升级到新版本。例如，`patch_0_9_2` 就是用于修补 vLLM 0.9.2 的。" + +#: ../../developer_guide/feature_guide/patch.md:42 +msgid "" +"`patch_main`: This module is used for patching the code in vLLM main branch." +msgstr "`patch_main`：该模块用于修补 vLLM 主分支代码。" + +#: ../../developer_guide/feature_guide/patch.md:43 +msgid "" +"`patch_common`: This module is used for patching both vLLM 0.9.2 and vLLM " +"main branch." +msgstr "`patch_common`：此模块用于同时修补 vLLM 0.9.2 版本和 vLLM 主分支。" + +#: ../../developer_guide/feature_guide/patch.md:45 +msgid "How to write a patch" +msgstr "如何撰写补丁" + +#: ../../developer_guide/feature_guide/patch.md:47 +msgid "" +"Before writing a patch, following the principle above, we should patch the " +"least code. If it's necessary, we can patch the code in either **platform** " +"and **worker** folder. Here is an example to patch `distributed` module in " +"vLLM." +msgstr "" +"在编写补丁之前，遵循上述原则，我们应尽量修改最少的代码。如果有必要，我们可以修改 **platform** 和 **worker** " +"文件夹中的代码。下面是一个在 vLLM 中修改 `distributed` 模块的示例。" + +#: ../../developer_guide/feature_guide/patch.md:49 +msgid "" +"Decide which version of vLLM we should patch. For example, after analysis, " +"here we want to patch both 0.9.2 and main of vLLM." +msgstr "决定我们应该修补哪个版本的 vLLM。例如，经过分析后，这里我们想要同时修补 vLLM 的 0.9.2 版和主分支（main）。" + +#: ../../developer_guide/feature_guide/patch.md:50 +msgid "" +"Decide which process we should patch. For example, here `distributed` " +"belongs to the vLLM main process, so we should patch `platform`." +msgstr "决定我们应该修补哪个进程。例如，这里 `distributed` 属于 vLLM 主进程，所以我们应该修补 `platform`。" + +#: ../../developer_guide/feature_guide/patch.md:51 +#, python-brace-format +msgid "" +"Create the patch file in the right folder. The file should be named as " +"`patch_{module_name}.py`. The example here is " +"`vllm_ascend/patch/platform/patch_common/patch_distributed.py`." +msgstr "" +"在正确的文件夹中创建补丁文件。文件应命名为 `patch_{module_name}.py`。此处的示例是 " +"`vllm_ascend/patch/platform/patch_common/patch_distributed.py`。" + +#: ../../developer_guide/feature_guide/patch.md:52 +msgid "Write your patch code in the new file. Here is an example:" +msgstr "在新文件中编写你的补丁代码。以下是一个示例：" + +#: ../../developer_guide/feature_guide/patch.md:62 +msgid "" +"Import the patch file in `__init__.py`. In this example, add `import " +"vllm_ascend.patch.platform.patch_common.patch_distributed` into " +"`vllm_ascend/patch/platform/patch_common/__init__.py`." +msgstr "" +"在 `__init__.py` 中导入补丁文件。在这个示例中，将 `import " +"vllm_ascend.patch.platform.patch_common.patch_distributed` 添加到 " +"`vllm_ascend/patch/platform/patch_common/__init__.py` 中。" + +#: ../../developer_guide/feature_guide/patch.md:63 +msgid "" +"Add the description of the patch in `vllm_ascend/patch/__init__.py`. The " +"description format is as follows:" +msgstr "在 `vllm_ascend/patch/__init__.py` 中添加补丁的描述。描述格式如下：" + +#: ../../developer_guide/feature_guide/patch.md:77 +msgid "" +"Add the Unit Test and E2E Test. Any newly added code in vLLM Ascend should " +"contain the Unit Test and E2E Test as well. You can find more details in " +"[test guide](../contribution/testing.md)" +msgstr "" +"添加单元测试和端到端（E2E）测试。在 vLLM Ascend 中新增的任何代码也应包含单元测试和端到端测试。更多详情请参见 " +"[测试指南](../contribution/testing.md)。" + +#: ../../developer_guide/feature_guide/patch.md:80 +msgid "Limitation" +msgstr "限制" + +#: ../../developer_guide/feature_guide/patch.md:81 +msgid "" +"In V1 Engine, vLLM starts three kinds of process: Main process, EngineCore " +"process and Worker process. Now vLLM Ascend only support patch the code in " +"Main process and Worker process by default. If you want to patch the code " +"runs in EngineCore process, you should patch EngineCore process entirely " +"during setup, the entry code is here `vllm.v1.engine.core`. Please override " +"`EngineCoreProc` and `DPEngineCoreProc` entirely." +msgstr "" +"在 V1 引擎中，vLLM 会启动三种类型的进程：主进程、EngineCore 进程和 Worker 进程。现在 vLLM Ascend " +"默认只支持在主进程和 Worker 进程中打补丁代码。如果你想要在 EngineCore 进程中打补丁，你需要在设置阶段对 EngineCore " +"进程整体打补丁，入口代码在 `vllm.v1.engine.core`。请完全重写 `EngineCoreProc` 和 " +"`DPEngineCoreProc`。" + +#: ../../developer_guide/feature_guide/patch.md:82 +msgid "" +"If you are running an edited vLLM code, the version of the vLLM may be " +"changed automatically. For example, if you runs an edited vLLM based on " +"v0.9.n, the version of vLLM may be change to v0.9.nxxx, in this case, the " +"patch for v0.9.n in vLLM Ascend would not work as expect, because that vLLM " +"Ascend can't distinguish the version of vLLM you're using. In this case, you" +" can set the environment variable `VLLM_VERSION` to specify the version of " +"vLLM you're using, then the patch for v0.9.2 should work." +msgstr "" +"如果你运行的是经过编辑的 vLLM 代码，vLLM 的版本可能会被自动更改。例如，如果你基于 v0.9.n 运行了编辑后的 vLLM，vLLM " +"的版本可能会变为 v0.9.nxxx，在这种情况下，vLLM Ascend 的 v0.9.n 补丁将无法正常工作，因为 vLLM Ascend " +"无法区分你所使用的 vLLM 版本。这时，你可以设置环境变量 `VLLM_VERSION` 来指定你所使用的 vLLM 版本，这样对 v0.9.2 " +"的补丁就应该可以正常工作。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_model.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_model.po new file mode 100644 index 000000000..09f8f9e94 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_model.po @@ -0,0 +1,333 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/modeling/adding_a_new_model.md:1 +msgid "Adding a New Model" +msgstr "添加新模型" + +#: ../../developer_guide/modeling/adding_a_new_model.md:3 +msgid "" +"This guide demonstrates how to integrate a novel or customized model into " +"vllm-ascend. For foundational concepts, it is highly recommended to refer to" +" [vllm official doc: Adding a New " +"Model](https://docs.vllm.ai/en/stable/contributing/model/) first." +msgstr "" +"本指南演示如何将新颖或自定义的模型集成到 vllm-ascend 中。对于基础概念，强烈建议先参考 [vllm " +"官方文档：添加新模型](https://docs.vllm.ai/en/stable/contributing/model/)。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:6 +msgid "Step 1: Implementing Models with `torch` and `torch_npu`" +msgstr "步骤 1：使用 `torch` 和 `torch_npu` 实现模型" + +#: ../../developer_guide/modeling/adding_a_new_model.md:8 +msgid "" +"This section provides instructions for implementing new models compatible " +"with vllm and vllm-ascend." +msgstr "本节提供了实现与 vllm 和 vllm-ascend 兼容的新模型的相关说明。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:10 +msgid "**Before starting:**" +msgstr "**开始之前：**" + +#: ../../developer_guide/modeling/adding_a_new_model.md:12 +msgid "" +"Verify whether your model already exists in vllm's " +"[models](https://github.com/vllm-" +"project/vllm/tree/main/vllm/model_executor/models) directory." +msgstr "" +"请确认你的模型是否已经存在于 vllm 的 [models](https://github.com/vllm-" +"project/vllm/tree/main/vllm/model_executor/models) 目录中。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:13 +msgid "" +"Use existing models' implementation as templates to accelerate your " +"development." +msgstr "使用已有模型的实现作为模板以加速您的开发。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:15 +msgid "Method 1: Implementing New Models from Scratch" +msgstr "方法一：从零开始实现新模型" + +#: ../../developer_guide/modeling/adding_a_new_model.md:17 +msgid "" +"Follow vllm's [OPT model " +"adaptation](https://docs.vllm.ai/en/stable/contributing/model/basic.html) " +"example for guidance." +msgstr "" +"请参考 vllm 的 [OPT " +"模型适配](https://docs.vllm.ai/en/stable/contributing/model/basic.html) 示例进行操作。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:19 +msgid "**Key implementation requirements:**" +msgstr "**关键实现要求：**" + +#: ../../developer_guide/modeling/adding_a_new_model.md:21 +msgid "Place model files in `vllm_ascend/models/` directory." +msgstr "请将模型文件放在 `vllm_ascend/models/` 目录下。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:23 +msgid "" +"Standard module structure for decoder-only LLMs (please checkout vllm's " +"implementations for other kinds of model):" +msgstr "解码器-only LLMs 的标准模块结构（请参考 vllm 对其他类型模型的实现）：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:25 +msgid "`*ModelForCausalLM` (top-level wrapper)" +msgstr "`*ModelForCausalLM`（顶层包装器）" + +#: ../../developer_guide/modeling/adding_a_new_model.md:26 +msgid "`*Model` (main architecture)" +msgstr "`*Model`（主架构）" + +#: ../../developer_guide/modeling/adding_a_new_model.md:27 +msgid "`*DecoderLayer` (transformer block)" +msgstr "`*DecoderLayer` （transformer 块）" + +#: ../../developer_guide/modeling/adding_a_new_model.md:28 +msgid "`*Attention` and `*MLP` (specific computation unit)" +msgstr "`*Attention` 和 `*MLP`（特定计算单元）" + +#: ../../developer_guide/modeling/adding_a_new_model.md:31 +msgid "`*` denotes your model's unique identifier." +msgstr "`*` 表示你的模型的唯一标识符。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:34 +msgid "Critical Implementation Details:" +msgstr "关键实现细节：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:36 +msgid "All modules must include a `prefix` argument in `__init__()`." +msgstr "所有模块在 `__init__()` 方法中都必须包含一个 `prefix` 参数。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:38 +msgid "**Required interfaces:**" +msgstr "**必需的接口：**" + +#: ../../developer_guide/modeling/adding_a_new_model.md:30 +msgid "Module Type" +msgstr "模块类型" + +#: ../../developer_guide/modeling/adding_a_new_model.md:30 +msgid "Required Methods" +msgstr "必需的方法" + +#: ../../developer_guide/modeling/adding_a_new_model.md:30 +msgid "`*ModelForCausalLM`" +msgstr "`*ModelForCausalLM`" + +#: ../../developer_guide/modeling/adding_a_new_model.md:30 +msgid "`get_input_embeddings`, `compute_logits`, `load_weights`" +msgstr "`get_input_embeddings`，`compute_logits`，`load_weights`" + +#: ../../developer_guide/modeling/adding_a_new_model.md:30 +msgid "`*Model`" +msgstr "`*模型`" + +#: ../../developer_guide/modeling/adding_a_new_model.md:30 +msgid "`get_input_embeddings`, `load_weights`" +msgstr "`get_input_embeddings`，`load_weights`" + +#: ../../developer_guide/modeling/adding_a_new_model.md:45 +msgid "Attention Backend Integration:" +msgstr "注意后端集成：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:47 +msgid "" +"Importing attention via `from vllm.attention import Attention` can " +"automatically leverage the attention backend routing of vllm-ascend (see: " +"`get_attn_backend_cls()` in `vllm_ascend/platform.py`)." +msgstr "" +"通过 `from vllm.attention import Attention` 导入 attention 可以自动利用 vllm-ascend " +"的注意力后端路由（详见：`vllm_ascend/platform.py` 中的 `get_attn_backend_cls()`）。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:49 +msgid "Tensor Parallelism:" +msgstr "张量并行：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:51 +msgid "" +"Use vllm's parallel layers (`ColumnParallelLinear`, " +"`VocabParallelEmbedding`, etc.) to implement models supporting tensor " +"parallelism. Note that Ascend-specific customizations are implemented in " +"`vllm_ascend/ops/` directory (RMSNorm, VocabParallelEmbedding, etc.)." +msgstr "" +"使用 vllm 的并行层（如 `ColumnParallelLinear`、`VocabParallelEmbedding` " +"等）来实现支持张量并行的模型。需要注意的是，Ascend 特有的自定义实现（如 RMSNorm、VocabParallelEmbedding 等）位于 " +"`vllm_ascend/ops/` 目录下。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:53 +msgid "" +"**Reference Implementation Template** (assumed path: " +"`vllm_ascend/models/custom_model.py`):" +msgstr "**参考实现模板**（假定路径：`vllm_ascend/models/custom_model.py`）：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:135 +msgid "Method 2: Customizing Existing vLLM Models" +msgstr "方法二：自定义已有的 vLLM 模型" + +#: ../../developer_guide/modeling/adding_a_new_model.md:137 +msgid "" +"For most use cases, extending existing implementations is preferable. We " +"demonstrate an example to inherit from base classes and implement a custom " +"deepseek model below (assumed path: `vllm_ascend/models/deepseek_v2.py`)." +msgstr "" +"对于大多数使用场景，建议扩展已有的实现。我们在下面演示了一个示例，通过继承基类并实现一个自定义的 deepseek " +"模型（假定路径：`vllm_ascend/models/deepseek_v2.py`）。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:175 +msgid "" +"For a complete implementation reference, see: " +"`vllm_ascend/models/deepseek_v2.py`." +msgstr "完整的实现参考请见：`vllm_ascend/models/deepseek_v2.py`。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:178 +msgid "Step 2: Registering Custom Models using ModelRegistry Plugins in vLLM" +msgstr "第2步：使用 vLLM 中的 ModelRegistry 插件注册自定义模型" + +#: ../../developer_guide/modeling/adding_a_new_model.md:180 +msgid "" +"vllm provides a plugin mechanism for registering externally implemented " +"models without modifying its codebase." +msgstr "vllm 提供了一种插件机制，可用于注册外部实现的模型，而无需修改其代码库。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:182 +msgid "" +"To integrate your implemented model from `vllm_ascend/models/` directory:" +msgstr "要集成你在 `vllm_ascend/models/` 目录下实现的模型：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:184 +msgid "" +"Import your model implementation in `vllm_ascend/models/__init__.py` using " +"relative imports." +msgstr "使用相对导入在 `vllm_ascend/models/__init__.py` 中导入你的模型实现。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:185 +msgid "" +"Register the model wrapper class via `vllm.ModelRegistry.register_model()` " +"function." +msgstr "通过 `vllm.ModelRegistry.register_model()` 函数注册模型包装类。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:187 +msgid "" +"**Reference Registration Template** (an example of registering new models in" +" `vllm_ascend/models/__init__.py`):" +msgstr "**参考注册模板**（在 `vllm_ascend/models/__init__.py` 注册新模型的示例）：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:210 +msgid "" +"The first argument of `vllm.ModelRegistry.register_model()` indicates the " +"unique architecture identifier which must match `architectures` in " +"`config.json` of the model." +msgstr "" +"`vllm.ModelRegistry.register_model()` 的第一个参数表示唯一的架构标识符，这个标识符必须与模型的 " +"`config.json` 文件中的 `architectures` 匹配。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:221 +msgid "Step 3: Verification" +msgstr "第 3 步：验证" + +#: ../../developer_guide/modeling/adding_a_new_model.md:223 +msgid "Case 1: Overriding Existing vLLM Model Architecture" +msgstr "案例 1：重载已有的 vLLM 模型架构" + +#: ../../developer_guide/modeling/adding_a_new_model.md:225 +msgid "" +"If you're registering a customized model architecture based on vllm's " +"existing implementation (overriding vllm's original class), when executing " +"vllm offline/online inference (using any model), you'll observe warning logs" +" similar to the following output from " +"`vllm/models_executor/models/registry.py`." +msgstr "" +"如果你基于 vllm 的现有实现注册了一个自定义的模型架构（覆盖了 vllm 的原始类），在执行 vllm " +"的离线/在线推理（无论使用哪个模型）时，你会看到类似于 `vllm/models_executor/models/registry.py` " +"输出的警告日志。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:231 +msgid "Case 2: Registering New Model Architecture" +msgstr "案例2：注册新模型架构" + +#: ../../developer_guide/modeling/adding_a_new_model.md:233 +msgid "" +"If you're registering a novel model architecture not present in vllm " +"(creating a completely new class), current logs won't provide explicit " +"confirmation by default. It's recommended to add the following logging " +"statement at the end of the `register_model` method in " +"`vllm/models_executor/models/registry.py`." +msgstr "" +"如果你注册了 vllm 中不存在的新模型架构（创建一个全新的类），当前日志默认不会提供明确的确认信息。建议在 " +"`vllm/models_executor/models/registry.py` 文件中的 `register_model` " +"方法末尾添加如下日志语句。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:239 +msgid "" +"After adding this line, you will see confirmation logs shown below when " +"running vllm offline/online inference (using any model)." +msgstr "添加这一行之后，当你运行 vllm 离线/在线推理（使用任何模型）时，将会看到如下确认日志。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:245 +msgid "" +"This log output confirms your novel model architecture has been successfully" +" registered in vllm." +msgstr "该日志输出确认了你的新模型架构已成功在 vllm 中注册。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:247 +msgid "Step 4: Testing" +msgstr "第4步：测试" + +#: ../../developer_guide/modeling/adding_a_new_model.md:249 +msgid "" +"After adding a new model, we should do basic functional test (offline/online" +" inference), accuracy test and performance benchmark for the model." +msgstr "在添加新模型后，我们应对该模型进行基本功能测试（离线/在线推理）、准确率测试和性能基准测试。" + +#: ../../developer_guide/modeling/adding_a_new_model.md:251 +msgid "Find more details at:" +msgstr "更多详情请见：" + +#: ../../developer_guide/modeling/adding_a_new_model.md:253 +msgid "" +"[Accuracy test guide](https://vllm-" +"ascend.readthedocs.io/en/latest/developer_guide/evaluation/index.html)" +msgstr "" +"[精度测试指南](https://vllm-" +"ascend.readthedocs.io/en/latest/developer_guide/evaluation/index.html)" + +#: ../../developer_guide/modeling/adding_a_new_model.md:254 +msgid "" +"[Performance benchmark guide](https://vllm-" +"ascend.readthedocs.io/en/latest/developer_guide/performance/performance_benchmark.html)" +msgstr "" +"[性能基准指南](https://vllm-" +"ascend.readthedocs.io/en/latest/developer_guide/performance/performance_benchmark.html)" + +#: ../../developer_guide/modeling/adding_a_new_model.md:256 +msgid "Step 5: Updating Supported Models Doc" +msgstr "第5步：更新支持的模型文档" + +#: ../../developer_guide/modeling/adding_a_new_model.md:258 +msgid "" +"At last, if all the steps above are completed, you should add the new model " +"into our [Supported Models](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/supported_models.html) doc." +msgstr "" +"最后，如果以上所有步骤都已完成，你应该将新模型添加到我们的[支持的模型](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/supported_models.html)文档中。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_multimodal_model.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_multimodal_model.po new file mode 100644 index 000000000..e0fd947a9 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/adding_a_new_multimodal_model.po @@ -0,0 +1,29 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/modeling/adding_a_new_multimodal_model.md:1 +msgid "Adding a New Multi-Modal Model" +msgstr "添加新的多模态模型" + +#: ../../developer_guide/modeling/adding_a_new_multimodal_model.md:3 +msgid "**_Comming soon ..._**" +msgstr "**_敬请期待 ..._**" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/index.po new file mode 100644 index 000000000..29a2982ff --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/modeling/index.po @@ -0,0 +1,32 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/modeling/index.md:1 +#: ../../developer_guide/modeling/index.md:5 +msgid "Modeling" +msgstr "新模型" + +#: ../../developer_guide/modeling/index.md:3 +msgid "" +"This section provides tutorials of how to implement and register a new model" +" into vllm-ascend." +msgstr "本节提供了如何在 vllm-ascend 中实现并注册新模型的教程。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/index.po new file mode 100644 index 000000000..c2b2e6fd4 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/index.po @@ -0,0 +1,26 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/performance/index.md:1 +#: ../../developer_guide/performance/index.md:3 +msgid "Performance" +msgstr "性能" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/performance_benchmark.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/performance_benchmark.po new file mode 100644 index 000000000..484edac36 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/performance_benchmark.po @@ -0,0 +1,88 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/performance/performance_benchmark.md:1 +msgid "Performance Benchmark" +msgstr "性能基准" + +#: ../../developer_guide/performance/performance_benchmark.md:2 +msgid "" +"This document details the benchmark methodology for vllm-ascend, aimed at " +"evaluating the performance under a variety of workloads. To maintain " +"alignment with vLLM, we use the [benchmark](https://github.com/vllm-" +"project/vllm/tree/main/benchmarks) script provided by the vllm project." +msgstr "" +"本文档详细说明了 vllm-ascend 的基准测试方法，旨在评估其在多种工作负载下的性能。为了与 vLLM 保持一致，我们使用 vllm 项目提供的 " +"[benchmark](https://github.com/vllm-project/vllm/tree/main/benchmarks) 脚本。" + +#: ../../developer_guide/performance/performance_benchmark.md:4 +msgid "" +"**Benchmark Coverage**: We measure offline e2e latency and throughput, and " +"fixed-QPS online serving benchmarks, for more details see [vllm-ascend " +"benchmark scripts](https://github.com/vllm-project/vllm-" +"ascend/tree/main/benchmarks)." +msgstr "" +"**基准测试覆盖范围**：我们测量离线端到端延迟和吞吐量，以及固定 QPS 的在线服务基准测试。更多详情请参见 [vllm-ascend " +"基准测试脚本](https://github.com/vllm-project/vllm-ascend/tree/main/benchmarks)。" + +#: ../../developer_guide/performance/performance_benchmark.md:6 +msgid "1. Run docker container" +msgstr "1. 运行 docker 容器" + +#: ../../developer_guide/performance/performance_benchmark.md:31 +msgid "2. Install dependencies" +msgstr "2. 安装依赖项" + +#: ../../developer_guide/performance/performance_benchmark.md:38 +msgid "3. (Optional)Prepare model weights" +msgstr "3.（可选）准备模型权重" + +#: ../../developer_guide/performance/performance_benchmark.md:39 +msgid "" +"For faster running speed, we recommend downloading the model in advance：" +msgstr "为了更快的运行速度，建议提前下载模型：" + +#: ../../developer_guide/performance/performance_benchmark.md:44 +msgid "" +"You can also replace all model paths in the [json](https://github.com/vllm-" +"project/vllm-ascend/tree/main/benchmarks/tests) files with your local paths:" +msgstr "" +"你也可以将 [json](https://github.com/vllm-project/vllm-" +"ascend/tree/main/benchmarks/tests) 文件中的所有模型路径替换为你的本地路径：" + +#: ../../developer_guide/performance/performance_benchmark.md:60 +msgid "4. Run benchmark script" +msgstr "4. 运行基准测试脚本" + +#: ../../developer_guide/performance/performance_benchmark.md:61 +msgid "Run benchmark script:" +msgstr "运行基准测试脚本：" + +#: ../../developer_guide/performance/performance_benchmark.md:66 +msgid "After about 10 mins, the output is as shown below:" +msgstr "大约 10 分钟后，输出如下所示：" + +#: ../../developer_guide/performance/performance_benchmark.md:176 +msgid "" +"The result json files are generated into the path `benchmark/results` These " +"files contain detailed benchmarking results for further analysis." +msgstr "结果 json 文件会生成到路径 `benchmark/results`。这些文件包含了用于进一步分析的详细基准测试结果。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/profile_execute_duration.po b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/profile_execute_duration.po new file mode 100644 index 000000000..7c83ca9bf --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance/profile_execute_duration.po @@ -0,0 +1,81 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../developer_guide/performance/profile_execute_duration.md:1 +msgid "Profile Execute Duration" +msgstr "配置执行持续时间" + +#: ../../developer_guide/performance/profile_execute_duration.md:3 +msgid "" +"The execution duration of each stage (including pre/post-processing, model " +"forward, etc.) usually needs to be captured during a complete inference " +"process. Typically, this is done by using `torch.npu.synchronize()` and " +"obtaining CPU timestamps, which increases the performance overhead of " +"host/device synchronization." +msgstr "" +"在完整的推理过程中，通常需要记录每个阶段（包括前/后处理、模型前向等）的执行时长。一般通过使用 `torch.npu.synchronize()` " +"并获取 CPU 时间戳来实现，这会增加主机/设备同步的性能开销。" + +#: ../../developer_guide/performance/profile_execute_duration.md:5 +msgid "" +"**To reduce the performance overhead, we add this feature, using the NPU " +"event timestamp mechanism to observe the device execution time " +"asynchronously.**" +msgstr "**为了减少性能开销，我们添加了此功能，使用 NPU 事件时间戳机制异步观测设备的执行时间。**" + +#: ../../developer_guide/performance/profile_execute_duration.md:7 +msgid "Usage" +msgstr "用法" + +#: ../../developer_guide/performance/profile_execute_duration.md:8 +msgid "" +"Use the environment variable `VLLM_ASCEND_MODEL_EXECUTE_TIME_OBSERVE` to " +"enable this feature." +msgstr "使用环境变量 `VLLM_ASCEND_MODEL_EXECUTE_TIME_OBSERVE` 来启用此功能。" + +#: ../../developer_guide/performance/profile_execute_duration.md:9 +msgid "" +"Use the non-blocking API `ProfileExecuteDuration().capture_async` to set " +"observation points asynchronously when you need to observe the execution " +"duration." +msgstr "" +"当你需要观察执行时长时，可以使用非阻塞 API `ProfileExecuteDuration().capture_async` 异步设置观察点。" + +#: ../../developer_guide/performance/profile_execute_duration.md:10 +msgid "" +"Use the blocking API `ProfileExecuteDuration().pop_captured_sync` at an " +"appropriate time to get and print the execution durations of all observed " +"stages." +msgstr "" +"在适当的时机使用阻塞式 API `ProfileExecuteDuration().pop_captured_sync` " +"获取并打印所有已观察到阶段的执行时长。" + +#: ../../developer_guide/performance/profile_execute_duration.md:12 +msgid "" +"**We have instrumented the key inference stages (including pre-processing, " +"model forward pass, etc.) for execute duration profiling. Execute the script" +" as follows:**" +msgstr "**我们已经对关键的推理阶段（包括预处理、模型前向传递等）进行了执行时长分析的检测。请按如下方式执行脚本：**" + +#: ../../developer_guide/performance/profile_execute_duration.md:17 +msgid "Example Output" +msgstr "示例输出" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/faqs.po b/docs/source/locale/zh_CN/LC_MESSAGES/faqs.po new file mode 100644 index 000000000..f961f09af --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/faqs.po @@ -0,0 +1,479 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../faqs.md:1 +msgid "FAQs" +msgstr "" + +#: ../../faqs.md:3 +msgid "Version Specific FAQs" +msgstr "特定版本常见问题" + +#: ../../faqs.md:5 +msgid "" +"[[v0.7.3.post1] FAQ & Feedback](https://github.com/vllm-project/vllm-" +"ascend/issues/1007)" +msgstr "" +"[[v0.7.3.post1] 常见问题与反馈](https://github.com/vllm-project/vllm-" +"ascend/issues/1007)" + +#: ../../faqs.md:6 +msgid "" +"[[v0.9.2rc1] FAQ & Feedback](https://github.com/vllm-project/vllm-" +"ascend/issues/1742)" +msgstr "" +"[[v0.9.2rc1] 常见问题与反馈](https://github.com/vllm-project/vllm-" +"ascend/issues/1742)" + +#: ../../faqs.md:8 +msgid "General FAQs" +msgstr "常见问题解答" + +#: ../../faqs.md:10 +msgid "1. What devices are currently supported?" +msgstr "1. 目前支持哪些设备？" + +#: ../../faqs.md:12 +msgid "" +"Currently, **ONLY** Atlas A2 series(Ascend-cann-kernels-910b) and Atlas " +"300I(Ascend-cann-kernels-310p) series are supported:" +msgstr "" +"目前，**仅**支持 Atlas A2 系列（Ascend-cann-kernels-910b）和 Atlas 300I（Ascend-cann-" +"kernels-310p）系列：" + +#: ../../faqs.md:14 +msgid "" +"Atlas A2 Training series (Atlas 800T A2, Atlas 900 A2 PoD, Atlas 200T A2 " +"Box16, Atlas 300T A2)" +msgstr "" +"Atlas A2 训练系列（Atlas 800T A2，Atlas 900 A2 PoD，Atlas 200T A2 Box16，Atlas 300T " +"A2）" + +#: ../../faqs.md:15 +msgid "Atlas 800I A2 Inference series (Atlas 800I A2)" +msgstr "Atlas 800I A2 推理系列（Atlas 800I A2）" + +#: ../../faqs.md:16 +msgid "Atlas 300I Inference series (Atlas 300I Duo)" +msgstr "Atlas 300I 推理系列（Atlas 300I Duo）" + +#: ../../faqs.md:18 +msgid "Below series are NOT supported yet:" +msgstr "以下系列目前尚不受支持：" + +#: ../../faqs.md:19 +msgid "Atlas 200I A2 (Ascend-cann-kernels-310b) unplanned yet" +msgstr "Atlas 200I A2（Ascend-cann-kernels-310b）尚未计划" + +#: ../../faqs.md:20 +msgid "Ascend 910, Ascend 910 Pro B (Ascend-cann-kernels-910) unplanned yet" +msgstr "Ascend 910，Ascend 910 Pro B（Ascend-cann-kernels-910）尚未计划" + +#: ../../faqs.md:22 +msgid "" +"From a technical view, vllm-ascend support would be possible if the torch-" +"npu is supported. Otherwise, we have to implement it by using custom ops. We" +" are also welcome to join us to improve together." +msgstr "" +"从技术角度来看，如果支持 torch-npu，则可以支持 vllm-ascend。否则，我们需要通过自定义算子来实现。我们也欢迎大家一起加入，共同改进。" + +#: ../../faqs.md:24 +msgid "2. How to get our docker containers?" +msgstr "2. 如何获取我们的 docker 容器？" + +#: ../../faqs.md:26 +msgid "" +"You can get our containers at `Quay.io`, e.g., [vllm-" +"ascend](https://quay.io/repository/ascend/vllm-ascend?tab=tags) and " +"[cann](https://quay.io/repository/ascend/cann?tab=tags)." +msgstr "" +"你可以在 `Quay.io` 获取我们的容器，例如，[vllm-" +"ascend](https://quay.io/repository/ascend/vllm-ascend?tab=tags) 和 " +"[cann](https://quay.io/repository/ascend/cann?tab=tags)。" + +#: ../../faqs.md:28 +msgid "" +"If you are in China, you can use `daocloud` to accelerate your downloading:" +msgstr "如果你在中国，可以使用 `daocloud` 来加速下载：" + +#: ../../faqs.md:36 +msgid "3. What models does vllm-ascend supports?" +msgstr "3. vllm-ascend 支持哪些模型？" + +#: ../../faqs.md:38 +msgid "" +"Find more details [here](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_models.html)." +msgstr "" +"在[此处](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_models.html)查看更多详细信息。" + +#: ../../faqs.md:40 +msgid "4. How to get in touch with our community?" +msgstr "4. 如何与我们的社区取得联系？" + +#: ../../faqs.md:42 +msgid "" +"There are many channels that you can communicate with our community " +"developers / users:" +msgstr "你可以通过多种渠道与我们的社区开发者/用户进行交流：" + +#: ../../faqs.md:44 +msgid "" +"Submit a GitHub [issue](https://github.com/vllm-project/vllm-" +"ascend/issues?page=1)." +msgstr "" +"提交一个 GitHub [issue](https://github.com/vllm-project/vllm-" +"ascend/issues?page=1)。" + +#: ../../faqs.md:45 +msgid "" +"Join our [weekly " +"meeting](https://docs.google.com/document/d/1hCSzRTMZhIB8vRq1_qOOjx4c9uYUxvdQvDsMV2JcSrw/edit?tab=t.0#heading=h.911qu8j8h35z)" +" and share your ideas." +msgstr "" +"加入我们的[每周会议](https://docs.google.com/document/d/1hCSzRTMZhIB8vRq1_qOOjx4c9uYUxvdQvDsMV2JcSrw/edit?tab=t.0#heading=h.911qu8j8h35z)，并分享你的想法。" + +#: ../../faqs.md:46 +msgid "" +"Join our [WeChat](https://github.com/vllm-project/vllm-" +"ascend/issues/227) group and ask your quenstions." +msgstr "" +"加入我们的 [微信群](https://github.com/vllm-project/vllm-ascend/issues/227) " +"并提问你的问题。" + +#: ../../faqs.md:47 +msgid "" +"Join our ascend channel in [vLLM " +"forums](https://discuss.vllm.ai/c/hardware-support/vllm-ascend-" +"support/6) and publish your topics." +msgstr "" +"加入我们在 [vLLM 论坛](https://discuss.vllm.ai/c/hardware-support/vllm-" +"ascend-support/6) 的 ascend 频道并发布你的话题。" + +#: ../../faqs.md:49 +msgid "5. What features does vllm-ascend V1 supports?" +msgstr "5. vllm-ascend V1 支持哪些功能？" + +#: ../../faqs.md:51 +msgid "" +"Find more details [here](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)." +msgstr "" +"在[这里](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)找到更多详细信息。" + +#: ../../faqs.md:53 +msgid "" +"6. How to solve the problem of \"Failed to infer device type\" or " +"\"libatb.so: cannot open shared object file\"?" +msgstr "6. 如何解决“无法推断设备类型”或“libatb.so：无法打开共享对象文件”问题？" + +#: ../../faqs.md:55 +msgid "" +"Basically, the reason is that the NPU environment is not configured " +"correctly. You can:" +msgstr "基本上，原因是 NPU 环境没有正确配置。你可以：" + +#: ../../faqs.md:56 +msgid "" +"try `source /usr/local/Ascend/nnal/atb/set_env.sh` to enable NNAL package." +msgstr "尝试运行 `source /usr/local/Ascend/nnal/atb/set_env.sh` 以启用 NNAL 包。" + +#: ../../faqs.md:57 +msgid "" +"try `source /usr/local/Ascend/ascend-toolkit/set_env.sh` to enable CANN " +"package." +msgstr "尝试运行 `source /usr/local/Ascend/ascend-toolkit/set_env.sh` 以启用 CANN 包。" + +#: ../../faqs.md:58 +msgid "try `npu-smi info` to check whether the NPU is working." +msgstr "尝试运行 `npu-smi info` 来检查 NPU 是否正常工作。" + +#: ../../faqs.md:60 +msgid "" +"If all above steps are not working, you can try the following code with " +"python to check whether there is any error:" +msgstr "如果以上所有步骤都无效，你可以尝试使用以下 python 代码来检查是否有错误：" + +#: ../../faqs.md:68 +msgid "" +"If all above steps are not working, feel free to submit a GitHub issue." +msgstr "如果以上所有步骤都无法解决问题，欢迎提交一个 GitHub issue。" + +#: ../../faqs.md:70 +msgid "7. How does vllm-ascend perform?" +msgstr "7. vllm-ascend 的性能如何？" + +#: ../../faqs.md:72 +msgid "" +"Currently, only some models are improved. Such as `Qwen2.5 VL`, `Qwen3`, " +"`Deepseek V3`. Others are not good enough. From 0.9.0rc2, Qwen and Deepseek" +" works with graph mode to play a good performance. What's more, you can " +"install `mindie-turbo` with `vllm-ascend v0.7.3` to speed up the inference " +"as well." +msgstr "" +"目前，只有部分模型得到了改进，比如 `Qwen2.5 VL`、`Qwen3` 和 `Deepseek V3`。其他模型的效果还不够理想。从 " +"0.9.0rc2 开始，Qwen 和 Deepseek 已经支持图模式，以获得更好的性能。此外，你还可以在 `vllm-ascend v0.7.3` " +"上安装 `mindie-turbo`，进一步加速推理。" + +#: ../../faqs.md:74 +msgid "8. How vllm-ascend work with vllm?" +msgstr "8. vllm-ascend 如何与 vllm 协同工作？" + +#: ../../faqs.md:75 +msgid "" +"vllm-ascend is a plugin for vllm. Basically, the version of vllm-ascend is " +"the same as the version of vllm. For example, if you use vllm 0.7.3, you " +"should use vllm-ascend 0.7.3 as well. For main branch, we will make sure " +"`vllm-ascend` and `vllm` are compatible by each commit." +msgstr "" +"vllm-ascend 是 vllm 的一个插件。基本上，vllm-ascend 的版本与 vllm 的版本是相同的。例如，如果你使用 vllm " +"0.7.3，你也应该使用 vllm-ascend 0.7.3。对于主分支，我们会确保每次提交都让 `vllm-ascend` 和 `vllm` " +"保持兼容。" + +#: ../../faqs.md:77 +msgid "9. Does vllm-ascend support Prefill Disaggregation feature?" +msgstr "9. vllm-ascend 支持 Prefill Disaggregation 功能吗？" + +#: ../../faqs.md:79 +msgid "" +"Currently, only 1P1D is supported on V0 Engine. For V1 Engine or NPND " +"support, We will make it stable and supported by vllm-ascend in the future." +msgstr "目前，V0引擎只支持1P1D。对于V1引擎或NPND的支持，我们将在未来使其稳定并由vllm-ascend支持。" + +#: ../../faqs.md:81 +msgid "10. Does vllm-ascend support quantization method?" +msgstr "10. vllm-ascend 支持量化方法吗？" + +#: ../../faqs.md:83 +msgid "" +"Currently, w8a8 quantization is already supported by vllm-ascend originally " +"on v0.8.4rc2 or higher, If you're using vllm 0.7.3 version, w8a8 " +"quantization is supporeted with the integration of vllm-ascend and mindie-" +"turbo, please use `pip install vllm-ascend[mindie-turbo]`." +msgstr "" +"目前，w8a8 量化已在 v0.8.4rc2 或更高版本的 vllm-ascend 中原生支持。如果你使用的是 vllm 0.7.3 版本，集成了 " +"vllm-ascend 和 mindie-turbo 后也支持 w8a8 量化，请使用 `pip install vllm-ascend[mindie-" +"turbo]`。" + +#: ../../faqs.md:85 +msgid "11. How to run w8a8 DeepSeek model?" +msgstr "11. 如何运行 w8a8 DeepSeek 模型？" + +#: ../../faqs.md:87 +msgid "" +"Please following the [inferencing tutorail](https://vllm-" +"ascend.readthedocs.io/en/latest/tutorials/multi_node.html) and replace model" +" to DeepSeek." +msgstr "" +"请按照[inferencing 教程](https://vllm-" +"ascend.readthedocs.io/en/latest/tutorials/multi_node.html)进行操作，并将模型更换为 " +"DeepSeek。" + +#: ../../faqs.md:89 +msgid "" +"12. There is no output in log when loading models using vllm-ascend, How to " +"solve it?" +msgstr "12. 使用 vllm-ascend 加载模型时日志没有输出，如何解决？" + +#: ../../faqs.md:91 +msgid "" +"If you're using vllm 0.7.3 version, this is a known progress bar display " +"issue in VLLM, which has been resolved in [this PR](https://github.com/vllm-" +"project/vllm/pull/12428), please cherry-pick it locally by yourself. " +"Otherwise, please fill up an issue." +msgstr "" +"如果你正在使用 vllm 0.7.3 版本，这是 VLLM 已知的进度条显示问题，已在 [此 PR](https://github.com/vllm-" +"project/vllm/pull/12428) 中解决，请自行在本地进行 cherry-pick。否则，请提交一个 issue。" + +#: ../../faqs.md:93 +msgid "13. How vllm-ascend is tested" +msgstr "13. 如何测试 vllm-ascend" + +#: ../../faqs.md:95 +msgid "" +"vllm-ascend is tested by functional test, performance test and accuracy " +"test." +msgstr "vllm-ascend 经过功能测试、性能测试和精度测试。" + +#: ../../faqs.md:97 +msgid "" +"**Functional test**: we added CI, includes portion of vllm's native unit " +"tests and vllm-ascend's own unit tests，on vllm-ascend's test, we test basic " +"functionality、popular models availability and [supported " +"features](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)" +" via e2e test" +msgstr "" +"**功能测试**：我们添加了CI，包含了vllm原生单元测试的一部分以及vllm-ascend自己的单元测试。在vllm-" +"ascend的测试中，我们通过e2e测试验证了基本功能、主流模型可用性和[支持的特性](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/support_matrix/supported_features.html)。" + +#: ../../faqs.md:99 +msgid "" +"**Performance test**: we provide [benchmark](https://github.com/vllm-" +"project/vllm-ascend/tree/main/benchmarks) tools for end-to-end performance " +"benchmark which can easily to re-route locally, we'll publish a perf website" +" to show the performance test results for each pull request" +msgstr "" +"**性能测试**：我们提供了用于端到端性能基准测试的[基准测试](https://github.com/vllm-project/vllm-" +"ascend/tree/main/benchmarks)工具，可以方便地在本地重新运行。我们将发布一个性能网站，用于展示每个拉取请求的性能测试结果。" + +#: ../../faqs.md:101 +msgid "" +"**Accuracy test**: we're working on adding accuracy test to CI as well." +msgstr "**准确性测试**：我们也在努力将准确性测试添加到CI中。" + +#: ../../faqs.md:103 +msgid "" +"Finnall, for each release, we'll publish the performance test and accuracy " +"test report in the future." +msgstr "最后，未来每个版本发布时，我们都会公开性能测试和准确性测试报告。" + +#: ../../faqs.md:105 +msgid "14. How to fix the error \"InvalidVersion\" when using vllm-ascend?" +msgstr "14. 使用 vllm-ascend 时如何解决 “InvalidVersion” 错误？" + +#: ../../faqs.md:106 +msgid "" +"It's usually because you have installed an dev/editable version of vLLM " +"package. In this case, we provide the env variable `VLLM_VERSION` to let " +"users specify the version of vLLM package to use. Please set the env " +"variable `VLLM_VERSION` to the version of vLLM package you have installed. " +"The format of `VLLM_VERSION` should be `X.Y.Z`." +msgstr "" +"这通常是因为你安装了开发版或可编辑版本的 vLLM 包。在这种情况下，我们提供了环境变量 `VLLM_VERSION`，以便用户指定要使用的 vLLM " +"包版本。请将环境变量 `VLLM_VERSION` 设置为你已安装的 vLLM 包的版本。`VLLM_VERSION` 的格式应为 `X.Y.Z`。" + +#: ../../faqs.md:108 +msgid "15. How to handle Out Of Memory?" +msgstr "15. 如何处理内存溢出？" + +#: ../../faqs.md:109 +msgid "" +"OOM errors typically occur when the model exceeds the memory capacity of a " +"single NPU. For general guidance, you can refer to [vLLM's OOM " +"troubleshooting " +"documentation](https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#out-" +"of-memory)." +msgstr "" +"当模型超出单个 NPU 的内存容量时，通常会发生 OOM（内存溢出）错误。一般性的指导可以参考 [vLLM 的 OOM " +"故障排除文档](https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html#out-" +"of-memory)。" + +#: ../../faqs.md:111 +msgid "" +"In scenarios where NPUs have limited HBM (High Bandwidth Memory) capacity, " +"dynamic memory allocation/deallocation during inference can exacerbate " +"memory fragmentation, leading to OOM. To address this:" +msgstr "" +"在 NPU 的 HBM（高带宽内存）容量有限的场景下，推理过程中动态内存分配和释放会加剧内存碎片，从而导致 OOM（内存溢出）。为了解决这个问题：" + +#: ../../faqs.md:113 +msgid "" +"**Adjust `--gpu-memory-utilization`**: If unspecified, will use the default " +"value of `0.9`. You can decrease this param to reserve more memory to reduce" +" fragmentation risks. See more note in: [vLLM - Inference and Serving - " +"Engine " +"Arguments](https://docs.vllm.ai/en/latest/serving/engine_args.html#vllm.engine.arg_utils-" +"_engine_args_parser-cacheconfig)." +msgstr "" +"**调整 `--gpu-memory-utilization`**：如果未指定，将使用默认值 " +"`0.9`。你可以降低此参数来预留更多内存，从而降低内存碎片风险。参见更多说明：[vLLM - 推理与服务 - " +"引擎参数](https://docs.vllm.ai/en/latest/serving/engine_args.html#vllm.engine.arg_utils-" +"_engine_args_parser-cacheconfig)。" + +#: ../../faqs.md:115 +msgid "" +"**Configure `PYTORCH_NPU_ALLOC_CONF`**: Set this environment variable to " +"optimize NPU memory management. For example, you can `export " +"PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` to enable virtual memory " +"feature to mitigate memory fragmentation caused by frequent dynamic memory " +"size adjustments during runtime, see more note in: " +"[PYTORCH_NPU_ALLOC_CONF](https://www.hiascend.com/document/detail/zh/Pytorch/700/comref/Envvariables/Envir_012.html)." +msgstr "" +"**配置 `PYTORCH_NPU_ALLOC_CONF`**：设置此环境变量以优化NPU内存管理。例如，你可以通过 `export " +"PYTORCH_NPU_ALLOC_CONF=expandable_segments:True` " +"来启用虚拟内存功能，以缓解运行时频繁动态调整内存大小导致的内存碎片问题，更多说明参见：[PYTORCH_NPU_ALLOC_CONF](https://www.hiascend.com/document/detail/zh/Pytorch/700/comref/Envvariables/Envir_012.html)。" + +#: ../../faqs.md:117 +msgid "16. Failed to enable NPU graph mode when running DeepSeek?" +msgstr "16. 运行 DeepSeek 时无法启用 NPU 图模式？" + +#: ../../faqs.md:118 +#, python-brace-format +msgid "" +"You may encounter the following error if running DeepSeek with NPU graph " +"mode enabled. The allowed number of queries per kv when enabling both MLA " +"and Graph mode only support {32, 64, 128}, **Thus this is not supported for " +"DeepSeek-V2-Lite**, as it only has 16 attention heads. The NPU graph mode " +"support on DeepSeek-V2-Lite will be done in the future." +msgstr "" +"如果在启用NPU图模式（Graph " +"mode）运行DeepSeek时，您可能会遇到以下错误。当同时启用MLA和图模式时，每个kv允许的查询数只支持{32, 64, " +"128}，**因此这不支持DeepSeek-V2-Lite**，因为它只有16个注意力头。未来会增加对DeepSeek-V2-Lite在NPU图模式下的支持。" + +#: ../../faqs.md:120 +#, python-brace-format +msgid "" +"And if you're using DeepSeek-V3 or DeepSeek-R1, please make sure after the " +"tensor parallel split, num_heads / num_kv_heads in {32, 64, 128}." +msgstr "" +"如果你正在使用 DeepSeek-V3 或 DeepSeek-R1，请确保在张量并行切分后，num_heads / num_kv_heads 的值为 " +"{32, 64, 128} 中的一个。" + +#: ../../faqs.md:127 +msgid "" +"17. Failed to reinstall vllm-ascend from source after uninstalling vllm-" +"ascend?" +msgstr "17. 卸载 vllm-ascend 后无法从源码重新安装 vllm-ascend？" + +#: ../../faqs.md:128 +msgid "" +"You may encounter the problem of C compilation failure when reinstalling " +"vllm-ascend from source using pip. If the installation fails, it is " +"recommended to use `python setup.py install` to install, or use `python " +"setup.py clean` to clear the cache." +msgstr "" +"当你使用 pip 从源码重新安装 vllm-ascend 时，可能会遇到 C 编译失败的问题。如果安装失败，建议使用 `python setup.py " +"install` 进行安装，或者使用 `python setup.py clean` 清除缓存。" + +#: ../../faqs.md:130 +msgid "18. How to generate determinitic results when using vllm-ascend?" +msgstr "18. 使用 vllm-ascend 时如何生成确定性结果？" + +#: ../../faqs.md:131 +msgid "There are several factors that affect output certainty:" +msgstr "有几个因素会影响输出的确定性：" + +#: ../../faqs.md:133 +msgid "" +"Sampler Method: using **Greedy sample** by setting `temperature=0` in " +"`SamplingParams`, e.g.:" +msgstr "" +"采样方法：通过在 `SamplingParams` 中设置 `temperature=0` 来使用 **贪婪采样（Greedy " +"sample）**，例如：" + +#: ../../faqs.md:158 +msgid "Set the following enveriments parameters:" +msgstr "设置以下环境参数：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/index.po new file mode 100644 index 000000000..26834856d --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/index.po @@ -0,0 +1,79 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: 2025-07-18 10:05+0800\n" +"Last-Translator: \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" +"X-Generator: Poedit 3.5\n" + +#: ../../index.md:33 +msgid "Getting Started" +msgstr "快速开始" + +#: ../../index.md:43 +msgid "User Guide" +msgstr "用户指南" + +#: ../../index.md:53 +msgid "Developer Guide" +msgstr "开发者指南" + +#: ../../index.md:64 +msgid "Community" +msgstr "社区" + +#: ../../index.md:1 +msgid "Welcome to vLLM Ascend Plugin" +msgstr "欢迎使用 vLLM Ascend 插件" + +#: ../../index.md:3 +msgid "vLLM" +msgstr "vLLM" + +#: ../../index.md:24 +msgid "" +"vLLM Ascend plugin (vllm-ascend) is a community maintained hardware plugin " +"for running vLLM on the Ascend NPU." +msgstr "" +"vLLM Ascend 插件（vllm-ascend）是一个由社区维护的硬件插件，用于在 Ascend " +"NPU 上运行 vLLM。" + +#: ../../index.md:26 +msgid "" +"This plugin is the recommended approach for supporting the Ascend backend " +"within the vLLM community. It adheres to the principles outlined in the " +"[[RFC]: Hardware pluggable](https://github.com/vllm-project/vllm/" +"issues/11162), providing a hardware-pluggable interface that decouples the " +"integration of the Ascend NPU with vLLM." +msgstr "" +"该插件是 vLLM 社区推荐用于支持 Ascend 后端的方法。它遵循 [[RFC]: Hardware " +"pluggable](https://github.com/vllm-project/vllm/issues/11162) 中提出的原" +"则，提供了一个硬件可插拔接口，实现了 Ascend NPU 与 vLLM 集成的解耦。" + +#: ../../index.md:28 +msgid "" +"By using vLLM Ascend plugin, popular open-source models, including " +"Transformer-like, Mixture-of-Expert, Embedding, Multi-modal LLMs can run " +"seamlessly on the Ascend NPU." +msgstr "" +"通过使用 vLLM Ascend 插件，流行的开源模型，包括 Transformer 类、混合专家、" +"嵌入式、多模态大模型等，都可以在 Ascend NPU 上无缝运行。" + +#: ../../index.md:30 +msgid "Documentation" +msgstr "文档" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/installation.po b/docs/source/locale/zh_CN/LC_MESSAGES/installation.po new file mode 100644 index 000000000..5ed464b3d --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/installation.po @@ -0,0 +1,293 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: 2025-07-18 10:09+0800\n" +"Last-Translator: \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" +"X-Generator: Poedit 3.5\n" + +#: ../../installation.md:1 +msgid "Installation" +msgstr "安装" + +#: ../../installation.md:3 +msgid "This document describes how to install vllm-ascend manually." +msgstr "本文档介绍如何手动安装 vllm-ascend。" + +#: ../../installation.md:5 +msgid "Requirements" +msgstr "要求" + +#: ../../installation.md:7 +msgid "OS: Linux" +msgstr "操作系统：Linux" + +#: ../../installation.md:8 +msgid "Python: >= 3.9, < 3.12" +msgstr "Python：>= 3.9，< 3.12" + +#: ../../installation.md:9 +msgid "A hardware with Ascend NPU. It's usually the Atlas 800 A2 series." +msgstr "配备有昇腾NPU的硬件，通常是Atlas 800 A2系列。" + +#: ../../installation.md:10 +msgid "Software:" +msgstr "软件：" + +#: ../../installation.md +msgid "Software" +msgstr "软件" + +#: ../../installation.md +msgid "Supported version" +msgstr "支持的版本" + +#: ../../installation.md +msgid "Note" +msgstr "注释" + +#: ../../installation.md +msgid "CANN" +msgstr "CANN" + +#: ../../installation.md +msgid ">= 8.1.RC1" +msgstr ">= 8.1.RC1" + +#: ../../installation.md +msgid "Required for vllm-ascend and torch-npu" +msgstr "vllm-ascend 和 torch-npu 必需" + +#: ../../installation.md +msgid "torch-npu" +msgstr "torch-npu" + +#: ../../installation.md +msgid ">= 2.5.1.post1.dev20250619" +msgstr ">= 2.5.1.post1.dev20250619" + +#: ../../installation.md +msgid "" +"Required for vllm-ascend, No need to install manually, it will be auto " +"installed in below steps" +msgstr "vllm-ascend 必需，无需手动安装，后续步骤会自动安装。" + +#: ../../installation.md +msgid "torch" +msgstr "torch" + +#: ../../installation.md +msgid ">= 2.5.1" +msgstr ">= 2.5.1" + +#: ../../installation.md +msgid "Required for torch-npu and vllm" +msgstr "torch-npu 和 vllm 所需" + +#: ../../installation.md:18 +msgid "You have 2 way to install:" +msgstr "你有两种安装方式：" + +#: ../../installation.md:19 +msgid "" +"**Using pip**: first prepare env manually or via CANN image, then install " +"`vllm-ascend` using pip." +msgstr "" +"**使用 pip**：首先手动准备环境或通过 CANN 镜像准备环境，然后使用 pip 安装 " +"`vllm-ascend`。" + +#: ../../installation.md:20 +msgid "" +"**Using docker**: use the `vllm-ascend` pre-built docker image directly." +msgstr "**使用 docker**：直接使用 `vllm-ascend` 预构建的 docker 镜像。" + +#: ../../installation.md:22 +msgid "Configure a new environment" +msgstr "配置一个新环境" + +#: ../../installation.md:24 +msgid "" +"Before installing, you need to make sure firmware/driver and CANN are " +"installed correctly, refer to [link](https://ascend.github.io/docs/sources/" +"ascend/quick_install.html) for more details." +msgstr "" +"在安装之前，您需要确保固件/驱动和 CANN 已正确安装，更多详情请参考 [链接]" +"(https://ascend.github.io/docs/sources/ascend/quick_install.html)。" + +#: ../../installation.md:26 +msgid "Configure hardware environment" +msgstr "配置硬件环境" + +#: ../../installation.md:28 +msgid "" +"To verify that the Ascend NPU firmware and driver were correctly installed, " +"run:" +msgstr "要验证 Ascend NPU 固件和驱动程序是否正确安装，请运行：" + +#: ../../installation.md:34 +msgid "" +"Refer to [Ascend Environment Setup Guide](https://ascend.github.io/docs/" +"sources/ascend/quick_install.html) for more details." +msgstr "" +"更多详情请参考[Ascend环境搭建指南](https://ascend.github.io/docs/sources/" +"ascend/quick_install.html)。" + +#: ../../installation.md:36 +msgid "Configure software environment" +msgstr "配置软件环境" + +#: ../../installation.md +msgid "Before using pip" +msgstr "在使用 pip 之前" + +#: ../../installation.md:46 +msgid "" +"The easiest way to prepare your software environment is using CANN image " +"directly:" +msgstr "最简单的方式是直接使用 CANN 镜像来准备您的软件环境：" + +#: ../../installation.md +msgid "Click here to see \"Install CANN manually\"" +msgstr "点击此处查看“手动安装 CANN”" + +#: ../../installation.md:72 +msgid "You can also install CANN manually:" +msgstr "你也可以手动安装 CANN：" + +#: ../../installation.md +msgid "Before using docker" +msgstr "在使用 docker 之前" + +#: ../../installation.md:104 +msgid "" +"No more extra step if you are using `vllm-ascend` prebuilt docker image." +msgstr "如果你使用 `vllm-ascend` 预构建的 docker 镜像，就无需额外的步骤。" + +#: ../../installation.md:108 +msgid "Once it's done, you can start to set up `vllm` and `vllm-ascend`." +msgstr "完成后，你可以开始配置 `vllm` 和 `vllm-ascend`。" + +#: ../../installation.md:110 +msgid "Setup vllm and vllm-ascend" +msgstr "安装 vllm 和 vllm-ascend" + +#: ../../installation.md +msgid "Using pip" +msgstr "使用 pip" + +#: ../../installation.md:121 +msgid "First install system dependencies and config pip mirror:" +msgstr "首先安装系统依赖并配置 pip 镜像：" + +#: ../../installation.md:133 +msgid "" +"**[Optional]** Then config the extra-index of `pip` if you are working on a " +"x86 machine or using torch-npu dev version:" +msgstr "" +"**[可选]** 如果你在 x86 机器上工作或使用 torch-npu 开发版，请配置 `pip` 的额" +"外索引：" + +#: ../../installation.md:140 +msgid "" +"Then you can install `vllm` and `vllm-ascend` from **pre-built wheel**:" +msgstr "然后你可以从**预编译的 wheel 包**安装 `vllm` 和 `vllm-ascend`：" + +#: ../../installation.md +msgid "Click here to see \"Build from source code\"" +msgstr "点击此处查看“从源代码构建”" + +#: ../../installation.md:153 +msgid "or build from **source code**:" +msgstr "或者从**源代码**构建：" + +#: ../../installation.md:171 +msgid "" +"vllm-ascend will build custom ops by default. If you don't want to build " +"it, set `COMPILE_CUSTOM_KERNELS=0` environment to disable it." +msgstr "" +"vllm-ascend 默认会编译自定义算子。如果你不想编译它，可以设置环境变量 " +"`COMPILE_CUSTOM_KERNELS=0` 来禁用。" + +#: ../../installation.md:175 +msgid "" +"If you are building from v0.7.3-dev and intend to use sleep mode feature, " +"you should set `COMPILE_CUSTOM_KERNELS=1` manually. To build custom ops, " +"gcc/g++ higher than 8 and c++ 17 or higher is required. If you're using " +"`pip install -e .` and encourage a torch-npu version conflict, please " +"install with `pip install --no-build-isolation -e .` to build on system " +"env. If you encounter other problems during compiling, it is probably " +"because unexpected compiler is being used, you may export `CXX_COMPILER` " +"and `C_COMPILER` in env to specify your g++ and gcc locations before " +"compiling." +msgstr "" +"如果你是从 v0.7.3-dev 版本开始构建，并且打算使用休眠模式功能，你需要手动设" +"置 `COMPILE_CUSTOM_KERNELS=1`。构建自定义算子时，要求 gcc/g++ 版本高于 8 且" +"支持 c++ 17 或更高标准。如果你正在使用 `pip install -e .` 并且出现了 torch-" +"npu 版本冲突，请使用 `pip install --no-build-isolation -e .` 在系统环境下进" +"行安装。如果在编译过程中遇到其它问题，可能是因为使用了非预期的编译器，你可以" +"在编译前通过环境变量导出 `CXX_COMPILER` 和 `C_COMPILER`，以指定你的 g++ 和 " +"gcc 路径。" + +#: ../../installation.md +msgid "Using docker" +msgstr "使用 docker" + +#: ../../installation.md:184 +msgid "You can just pull the **prebuilt image** and run it with bash." +msgstr "你可以直接拉取**预构建镜像**并用 bash 运行它。" + +#: ../../installation.md +msgid "Click here to see \"Build from Dockerfile\"" +msgstr "点击这里查看“从 Dockerfile 构建”" + +#: ../../installation.md:187 +msgid "or build IMAGE from **source code**:" +msgstr "或从**源代码**构建 IMAGE：" + +#: ../../installation.md:218 +msgid "" +"The default workdir is `/workspace`, vLLM and vLLM Ascend code are placed " +"in `/vllm-workspace` and installed in [development mode](https://setuptools." +"pypa.io/en/latest/userguide/development_mode.html)(`pip install -e`) to " +"help developer immediately take place changes without requiring a new " +"installation." +msgstr "" +"默认的工作目录是 `/workspace`，vLLM 和 vLLM Ascend 代码被放置在 `/vllm-" +"workspace`，并以[开发模式](https://setuptools.pypa.io/en/latest/userguide/" +"development_mode.html)（`pip install -e`）安装，以便开发者能够即时生效更改，" +"而无需重新安装。" + +#: ../../installation.md:222 +msgid "Extra information" +msgstr "额外信息" + +#: ../../installation.md:224 +msgid "Verify installation" +msgstr "验证安装" + +#: ../../installation.md:226 +msgid "Create and run a simple inference test. The `example.py` can be like:" +msgstr "创建并运行一个简单的推理测试。`example.py` 可以如下：" + +#: ../../installation.md:251 +msgid "Then run:" +msgstr "然后运行：" + +#: ../../installation.md:259 +msgid "The output will be like:" +msgstr "输出将会像这样：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/quick_start.po b/docs/source/locale/zh_CN/LC_MESSAGES/quick_start.po new file mode 100644 index 000000000..ebe66fddf --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/quick_start.po @@ -0,0 +1,149 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: 2025-07-18 10:09+0800\n" +"Last-Translator: \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" +"X-Generator: Poedit 3.5\n" + +#: ../../quick_start.md:1 +msgid "Quickstart" +msgstr "快速入门" + +#: ../../quick_start.md:3 +msgid "Prerequisites" +msgstr "先决条件" + +#: ../../quick_start.md:5 +msgid "Supported Devices" +msgstr "支持的设备" + +#: ../../quick_start.md:6 +msgid "" +"Atlas A2 Training series (Atlas 800T A2, Atlas 900 A2 PoD, Atlas 200T A2 " +"Box16, Atlas 300T A2)" +msgstr "" +"Atlas A2 训练系列（Atlas 800T A2，Atlas 900 A2 PoD，Atlas 200T A2 Box16，" +"Atlas 300T A2）" + +#: ../../quick_start.md:7 +msgid "Atlas 800I A2 Inference series (Atlas 800I A2)" +msgstr "Atlas 800I A2 推理系列（Atlas 800I A2）" + +#: ../../quick_start.md:9 +msgid "Setup environment using container" +msgstr "使用容器设置环境" + +#: ../../quick_start.md +msgid "Ubuntu" +msgstr "Ubuntu" + +#: ../../quick_start.md +msgid "openEuler" +msgstr "openEuler" + +#: ../../quick_start.md:69 +msgid "" +"The default workdir is `/workspace`, vLLM and vLLM Ascend code are placed " +"in `/vllm-workspace` and installed in [development mode](https://setuptools." +"pypa.io/en/latest/userguide/development_mode.html)(`pip install -e`) to " +"help developer immediately take place changes without requiring a new " +"installation." +msgstr "" +"默认的工作目录是 `/workspace`，vLLM 和 vLLM Ascend 代码被放置在 `/vllm-" +"workspace`，并以[开发模式](https://setuptools.pypa.io/en/latest/userguide/" +"development_mode.html)（`pip install -e`）安装，以便开发者能够即时生效更改，" +"而无需重新安装。" + +#: ../../quick_start.md:71 +msgid "Usage" +msgstr "用法" + +#: ../../quick_start.md:73 +msgid "You can use Modelscope mirror to speed up download:" +msgstr "你可以使用 Modelscope 镜像来加速下载：" + +#: ../../quick_start.md:80 +msgid "There are two ways to start vLLM on Ascend NPU:" +msgstr "在昇腾 NPU 上启动 vLLM 有两种方式：" + +#: ../../quick_start.md +msgid "Offline Batched Inference" +msgstr "离线批量推理" + +#: ../../quick_start.md:86 +msgid "" +"With vLLM installed, you can start generating texts for list of input " +"prompts (i.e. offline batch inferencing)." +msgstr "" +"安装了 vLLM 后，您可以开始为一系列输入提示生成文本（即离线批量推理）。" + +#: ../../quick_start.md:88 +msgid "" +"Try to run below Python script directly or use `python3` shell to generate " +"texts:" +msgstr "" +"尝试直接运行下面的 Python 脚本，或者使用 `python3` 交互式命令行来生成文本：" + +#: ../../quick_start.md +msgid "OpenAI Completions API" +msgstr "OpenAI Completions API" + +#: ../../quick_start.md:114 +msgid "" +"vLLM can also be deployed as a server that implements the OpenAI API " +"protocol. Run the following command to start the vLLM server with the [Qwen/" +"Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) " +"model:" +msgstr "" +"vLLM 也可以作为实现 OpenAI API 协议的服务器进行部署。运行以下命令，使用 " +"[Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-" +"Instruct) 模型启动 vLLM 服务器：" + +#: ../../quick_start.md:124 +msgid "If you see log as below:" +msgstr "如果你看到如下日志：" + +#: ../../quick_start.md:132 +msgid "Congratulations, you have successfully started the vLLM server!" +msgstr "恭喜，你已经成功启动了 vLLM 服务器！" + +#: ../../quick_start.md:134 +msgid "You can query the list the models:" +msgstr "你可以查询模型列表：" + +#: ../../quick_start.md:141 +msgid "You can also query the model with input prompts:" +msgstr "你也可以通过输入提示来查询模型：" + +#: ../../quick_start.md:155 +msgid "" +"vLLM is serving as background process, you can use `kill -2 $VLLM_PID` to " +"stop the background process gracefully, it's equal to `Ctrl-C` to stop " +"foreground vLLM process:" +msgstr "" +"vLLM 正作为后台进程运行，你可以使用 `kill -2 $VLLM_PID` 来优雅地停止后台进" +"程，这等同于使用 `Ctrl-C` 停止前台 vLLM 进程：" + +#: ../../quick_start.md:164 +msgid "You will see output as below:" +msgstr "你将会看到如下输出：" + +#: ../../quick_start.md:172 +msgid "Finally, you can exit container by using `ctrl-D`." +msgstr "最后，你可以通过按 `ctrl-D` 退出容器。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/index.po new file mode 100644 index 000000000..49292c43a --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/index.po @@ -0,0 +1,29 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/index.md:3 +msgid "Deployment" +msgstr "部署" + +#: ../../tutorials/index.md:1 +msgid "Tutorials" +msgstr "教程" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_node.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_node.po new file mode 100644 index 000000000..b7bdb9962 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_node.po @@ -0,0 +1,192 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/multi_node.md:1 +msgid "Multi-Node-DP (DeepSeek)" +msgstr "多节点分布式处理（DeepSeek）" + +#: ../../tutorials/multi_node.md:3 +msgid "Getting Start" +msgstr "快速开始" + +#: ../../tutorials/multi_node.md:4 +msgid "" +"vLLM-Ascend now supports Data Parallel (DP) deployment, enabling model " +"weights to be replicated across multiple NPUs or instances, each processing " +"independent batches of requests. This is particularly useful for scaling " +"throughput across devices while maintaining high resource utilization." +msgstr "" +"vLLM-Ascend 现在支持数据并行（DP）部署，可以在多个 NPU " +"或实例之间复制模型权重，每个实例处理独立的请求批次。这对于在保证高资源利用率的同时，实现跨设备的吞吐量扩展特别有用。" + +#: ../../tutorials/multi_node.md:6 +msgid "" +"Each DP rank is deployed as a separate “core engine” process which " +"communicates with front-end process(es) via ZMQ sockets. Data Parallel can " +"be combined with Tensor Parallel, in which case each DP engine owns a number" +" of per-NPU worker processes equal to the TP size." +msgstr "" +"每个 DP 进程作为一个单独的“核心引擎”进程部署，并通过 ZMQ 套接字与前端进程通信。数据并行可以与张量并行结合使用，此时每个 DP " +"引擎拥有数量等于 TP 大小的每 NPU 工作进程。" + +#: ../../tutorials/multi_node.md:8 +msgid "" +"For Mixture-of-Experts (MoE) models — especially advanced architectures like" +" DeepSeek that utilize Multi-head Latent Attention (MLA) — a hybrid " +"parallelism approach is recommended: - Use **Data Parallelism (DP)** for" +" attention layers, which are replicated across devices and handle separate " +"batches. - Use **Expert or Tensor Parallelism (EP/TP)** for expert " +"layers, which are sharded across devices to distribute the computation." +msgstr "" +"对于混合专家（Mixture-of-Experts, MoE）模型——尤其是像 DeepSeek 这样采用多头潜在注意力（Multi-head Latent Attention, MLA）的高级架构——推荐使用混合并行策略：\n" +" - 对于注意力层，使用 **数据并行（Data Parallelism, DP）**，这些层会在各设备间复刻，并处理不同的批次。\n" +" - 对于专家层，使用 **专家并行或张量并行（Expert or Tensor Parallelism, EP/TP）**，这些层会在设备间分片，从而分担计算。" + +#: ../../tutorials/multi_node.md:12 +msgid "" +"This division enables attention layers to be replicated across Data Parallel" +" (DP) ranks, enabling them to process different batches independently. " +"Meanwhile, expert layers are partitioned (sharded) across devices using " +"Expert or Tensor Parallelism(DP*TP), maximizing hardware utilization and " +"efficiency." +msgstr "" +"这种划分使得注意力层能够在数据并行（DP）组内复制，从而能够独立处理不同的批次。同时，专家层通过专家或张量并行（DP*TP）在设备间进行分区（切片），最大化硬件利用率和效率。" + +#: ../../tutorials/multi_node.md:14 +msgid "" +"In these cases the data parallel ranks are not completely independent, " +"forward passes must be aligned and expert layers across all ranks are " +"required to synchronize during every forward pass, even if there are fewer " +"requests to be processed than DP ranks." +msgstr "" +"在这些情况下，数据并行的各个 rank 不是完全独立的，前向传播必须对齐，并且所有 rank " +"上的专家层在每次前向传播时都需要同步，即使待处理的请求数量少于 DP rank 的数量。" + +#: ../../tutorials/multi_node.md:16 +msgid "" +"For MoE models, when any requests are in progress in any rank, we must " +"ensure that empty “dummy” forward passes are performed in all ranks which " +"don’t currently have any requests scheduled. This is handled via a separate " +"DP `Coordinator` process which communicates with all of the ranks, and a " +"collective operation performed every N steps to determine when all ranks " +"become idle and can be paused. When TP is used in conjunction with DP, " +"expert layers form an EP or TP group of size (DP x TP)." +msgstr "" +"对于 MoE 模型，当任何一个 rank 有请求正在进行时，必须确保所有当前没有请求的 rank 都执行空的“虚拟”前向传播。这是通过一个单独的 DP " +"`Coordinator` 协调器进程来实现的，该进程与所有 rank 通信，并且每隔 N 步执行一次集体操作，以判断所有 rank " +"是否都处于空闲状态并可以暂停。当 TP 与 DP 结合使用时，专家层会组成一个规模为（DP x TP）的 EP 或 TP 组。" + +#: ../../tutorials/multi_node.md:18 +msgid "Verify Multi-Node Communication Environment" +msgstr "验证多节点通信环境" + +#: ../../tutorials/multi_node.md:20 +msgid "Physical Layer Requirements:" +msgstr "物理层要求：" + +#: ../../tutorials/multi_node.md:22 +msgid "" +"The physical machines must be located on the same WLAN, with network " +"connectivity." +msgstr "物理机器必须位于同一个 WLAN 中，并且具有网络连接。" + +#: ../../tutorials/multi_node.md:23 +msgid "" +"All NPUs are connected with optical modules, and the connection status must " +"be normal." +msgstr "所有 NPU 都通过光模块连接，且连接状态必须正常。" + +#: ../../tutorials/multi_node.md:25 +msgid "Verification Process:" +msgstr "验证流程：" + +#: ../../tutorials/multi_node.md:27 +msgid "" +"Execute the following commands on each node in sequence. The results must " +"all be `success` and the status must be `UP`:" +msgstr "在每个节点上依次执行以下命令。所有结果必须为 `success` 且状态必须为 `UP`：" + +#: ../../tutorials/multi_node.md:44 +msgid "NPU Interconnect Verification:" +msgstr "NPU 互连验证：" + +#: ../../tutorials/multi_node.md:45 +msgid "1. Get NPU IP Addresses" +msgstr "1. 获取 NPU IP 地址" + +#: ../../tutorials/multi_node.md:50 +msgid "2. Cross-Node PING Test" +msgstr "2. 跨节点PING测试" + +#: ../../tutorials/multi_node.md:56 +msgid "Run with docker" +msgstr "用 docker 运行" + +#: ../../tutorials/multi_node.md:57 +msgid "" +"Assume you have two Atlas 800 A2(64G*8) nodes, and want to deploy the " +"`deepseek-v3-w8a8` quantitative model across multi-node." +msgstr "假设你有两台 Atlas 800 A2（64G*8）节点，并且想要在多节点上部署 `deepseek-v3-w8a8` 量化模型。" + +#: ../../tutorials/multi_node.md:92 +msgid "" +"Before launch the inference server, ensure some environment variables are " +"set for multi node communication" +msgstr "在启动推理服务器之前，确保已经为多节点通信设置了一些环境变量。" + +#: ../../tutorials/multi_node.md:95 +msgid "Run the following scripts on two nodes respectively" +msgstr "分别在两台节点上运行以下脚本" + +#: ../../tutorials/multi_node.md:97 +msgid "**node0**" +msgstr "**节点0**" + +#: ../../tutorials/multi_node.md:137 +msgid "**node1**" +msgstr "**节点1**" + +#: ../../tutorials/multi_node.md:176 +msgid "" +"The Deployment view looks like: ![alt text](../assets/multi_node_dp.png)" +msgstr "部署视图如下所示：![替代文本](../assets/multi_node_dp.png)" + +#: ../../tutorials/multi_node.md:176 +msgid "alt text" +msgstr "替代文本" + +#: ../../tutorials/multi_node.md:179 +msgid "" +"Once your server is started, you can query the model with input prompts:" +msgstr "一旦你的服务器启动，你可以通过输入提示词来查询模型：" + +#: ../../tutorials/multi_node.md:192 +msgid "Run benchmarks" +msgstr "运行基准测试" + +#: ../../tutorials/multi_node.md:193 +msgid "" +"For details please refer to [benchmark](https://github.com/vllm-" +"project/vllm-ascend/tree/main/benchmarks)" +msgstr "" +"详细信息请参阅 [benchmark](https://github.com/vllm-project/vllm-" +"ascend/tree/main/benchmarks)" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu.po new file mode 100644 index 000000000..512de8243 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu.po @@ -0,0 +1,62 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/multi_npu.md:1 +msgid "Multi-NPU (QwQ 32B)" +msgstr "多-NPU（QwQ 32B）" + +#: ../../tutorials/multi_npu.md:3 +msgid "Run vllm-ascend on Multi-NPU" +msgstr "在多NPU上运行 vllm-ascend" + +#: ../../tutorials/multi_npu.md:5 +msgid "Run docker container:" +msgstr "运行 docker 容器：" + +#: ../../tutorials/multi_npu.md:30 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/multi_npu.md:40 +msgid "Online Inference on Multi-NPU" +msgstr "多NPU的在线推理" + +#: ../../tutorials/multi_npu.md:42 +msgid "Run the following script to start the vLLM server on Multi-NPU:" +msgstr "运行以下脚本，在多NPU上启动 vLLM 服务器：" + +#: ../../tutorials/multi_npu.md:48 +msgid "" +"Once your server is started, you can query the model with input prompts" +msgstr "一旦服务器启动，就可以通过输入提示词来查询模型。" + +#: ../../tutorials/multi_npu.md:63 +msgid "Offline Inference on Multi-NPU" +msgstr "多NPU离线推理" + +#: ../../tutorials/multi_npu.md:65 +msgid "Run the following script to execute offline inference on multi-NPU:" +msgstr "运行以下脚本以在多NPU上执行离线推理：" + +#: ../../tutorials/multi_npu.md:102 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_moge.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_moge.po new file mode 100644 index 000000000..8718f0731 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_moge.po @@ -0,0 +1,86 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/multi_npu_moge.md:1 +msgid "Multi-NPU (Pangu Pro MoE)" +msgstr "多NPU（Pangu Pro MoE）" + +#: ../../tutorials/multi_npu_moge.md:3 +msgid "Run vllm-ascend on Multi-NPU" +msgstr "在多NPU上运行 vllm-ascend" + +#: ../../tutorials/multi_npu_moge.md:5 +msgid "Run container:" +msgstr "运行容器：" + +#: ../../tutorials/multi_npu_moge.md:30 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/multi_npu_moge.md:37 +msgid "Download the model:" +msgstr "下载该模型：" + +#: ../../tutorials/multi_npu_moge.md:44 +msgid "Online Inference on Multi-NPU" +msgstr "多NPU上的在线推理" + +#: ../../tutorials/multi_npu_moge.md:46 +msgid "Run the following script to start the vLLM server on Multi-NPU:" +msgstr "运行以下脚本，在多NPU上启动 vLLM 服务器：" + +#: ../../tutorials/multi_npu_moge.md:55 +msgid "" +"Once your server is started, you can query the model with input prompts:" +msgstr "一旦你的服务器启动，你可以通过输入提示词来查询模型：" + +#: ../../tutorials/multi_npu_moge.md +msgid "v1/completions" +msgstr "v1/补全" + +#: ../../tutorials/multi_npu_moge.md +msgid "v1/chat/completions" +msgstr "v1/chat/completions" + +#: ../../tutorials/multi_npu_moge.md:96 +msgid "If you run this successfully, you can see the info shown below:" +msgstr "如果你成功运行这个，你可以看到如下所示的信息：" + +#: ../../tutorials/multi_npu_moge.md:102 +msgid "Offline Inference on Multi-NPU" +msgstr "多NPU离线推理" + +#: ../../tutorials/multi_npu_moge.md:104 +msgid "Run the following script to execute offline inference on multi-NPU:" +msgstr "运行以下脚本以在多NPU上执行离线推理：" + +#: ../../tutorials/multi_npu_moge.md +msgid "Graph Mode" +msgstr "图模式" + +#: ../../tutorials/multi_npu_moge.md +msgid "Eager Mode" +msgstr "即时模式" + +#: ../../tutorials/multi_npu_moge.md:230 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_quantization.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_quantization.po new file mode 100644 index 000000000..63074351c --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_quantization.po @@ -0,0 +1,82 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/multi_npu_quantization.md:1 +msgid "Multi-NPU (QwQ 32B W8A8)" +msgstr "多NPU（QwQ 32B W8A8）" + +#: ../../tutorials/multi_npu_quantization.md:3 +msgid "Run docker container" +msgstr "运行 docker 容器" + +#: ../../tutorials/multi_npu_quantization.md:5 +msgid "w8a8 quantization feature is supported by v0.8.4rc2 or higher" +msgstr "w8a8 量化功能由 v0.8.4rc2 或更高版本支持" + +#: ../../tutorials/multi_npu_quantization.md:31 +msgid "Install modelslim and convert model" +msgstr "安装 modelslim 并转换模型" + +#: ../../tutorials/multi_npu_quantization.md:33 +msgid "" +"You can choose to convert the model yourself or use the quantized model we " +"uploaded, see https://www.modelscope.cn/models/vllm-ascend/QwQ-32B-W8A8" +msgstr "" +"你可以选择自己转换模型，或者使用我们上传的量化模型，详见 https://www.modelscope.cn/models/vllm-" +"ascend/QwQ-32B-W8A8" + +#: ../../tutorials/multi_npu_quantization.md:56 +msgid "Verify the quantized model" +msgstr "验证量化模型" + +#: ../../tutorials/multi_npu_quantization.md:57 +msgid "The converted model files looks like:" +msgstr "转换后的模型文件如下所示：" + +#: ../../tutorials/multi_npu_quantization.md:70 +msgid "" +"Run the following script to start the vLLM server with quantized model:" +msgstr "运行以下脚本以启动带有量化模型的 vLLM 服务器：" + +#: ../../tutorials/multi_npu_quantization.md:73 +msgid "" +"The value \"ascend\" for \"--quantization\" argument will be supported after" +" [a specific PR](https://github.com/vllm-project/vllm-ascend/pull/877) is " +"merged and released, you can cherry-pick this commit for now." +msgstr "" +"在 [特定的PR](https://github.com/vllm-project/vllm-ascend/pull/877) 合并并发布后， \"--" +"quantization\" 参数将支持值 \"ascend\"，你也可以现在手动挑选该提交。" + +#: ../../tutorials/multi_npu_quantization.md:79 +msgid "" +"Once your server is started, you can query the model with input prompts" +msgstr "一旦服务器启动，就可以通过输入提示词来查询模型。" + +#: ../../tutorials/multi_npu_quantization.md:93 +msgid "" +"Run the following script to execute offline inference on multi-NPU with " +"quantized model:" +msgstr "运行以下脚本，在多NPU上使用量化模型执行离线推理：" + +#: ../../tutorials/multi_npu_quantization.md:96 +msgid "To enable quantization for ascend, quantization method must be \"ascend\"" +msgstr "要在ascend上启用量化，量化方法必须为“ascend”。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_qwen3_moe.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_qwen3_moe.po new file mode 100644 index 000000000..71338938e --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/multi_npu_qwen3_moe.po @@ -0,0 +1,71 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/multi_npu_qwen3_moe.md:1 +msgid "Multi-NPU (Qwen3-30B-A3B)" +msgstr "多NPU（Qwen3-30B-A3B）" + +#: ../../tutorials/multi_npu_qwen3_moe.md:3 +msgid "Run vllm-ascend on Multi-NPU with Qwen3 MoE" +msgstr "在多NPU上运行带有Qwen3 MoE的vllm-ascend" + +#: ../../tutorials/multi_npu_qwen3_moe.md:5 +msgid "Run docker container:" +msgstr "运行 docker 容器：" + +#: ../../tutorials/multi_npu_qwen3_moe.md:30 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/multi_npu_qwen3_moe.md:40 +msgid "Online Inference on Multi-NPU" +msgstr "多NPU的在线推理" + +#: ../../tutorials/multi_npu_qwen3_moe.md:42 +msgid "Run the following script to start the vLLM server on Multi-NPU:" +msgstr "运行以下脚本以在多NPU上启动 vLLM 服务器：" + +#: ../../tutorials/multi_npu_qwen3_moe.md:44 +msgid "" +"For an Atlas A2 with 64GB of NPU card memory, tensor-parallel-size should be" +" at least 2, and for 32GB of memory, tensor-parallel-size should be at least" +" 4." +msgstr "" +"对于拥有64GB NPU卡内存的Atlas A2，tensor-parallel-size 至少应为2；对于32GB内存的NPU卡，tensor-" +"parallel-size 至少应为4。" + +#: ../../tutorials/multi_npu_qwen3_moe.md:50 +msgid "" +"Once your server is started, you can query the model with input prompts" +msgstr "一旦服务器启动，就可以通过输入提示词来查询模型。" + +#: ../../tutorials/multi_npu_qwen3_moe.md:65 +msgid "Offline Inference on Multi-NPU" +msgstr "多NPU离线推理" + +#: ../../tutorials/multi_npu_qwen3_moe.md:67 +msgid "Run the following script to execute offline inference on multi-NPU:" +msgstr "运行以下脚本以在多NPU上执行离线推理：" + +#: ../../tutorials/multi_npu_qwen3_moe.md:104 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_node_300i.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_node_300i.po new file mode 100644 index 000000000..530065d6c --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_node_300i.po @@ -0,0 +1,110 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/single_node_300i.md:1 +msgid "Single Node (Atlas 300I series)" +msgstr "单节点（Atlas 300I 系列）" + +#: ../../tutorials/single_node_300i.md:4 +msgid "" +"This Atlas 300I series is currently experimental. In future versions, there " +"may be behavioral changes around model coverage, performance improvement." +msgstr "Atlas 300I 系列目前处于实验阶段。在未来的版本中，模型覆盖范围和性能提升方面可能会有行为上的变化。" + +#: ../../tutorials/single_node_300i.md:7 +msgid "Run vLLM on Altlas 300I series" +msgstr "在 Altlas 300I 系列上运行 vLLM" + +#: ../../tutorials/single_node_300i.md:9 +msgid "Run docker container:" +msgstr "运行 docker 容器：" + +#: ../../tutorials/single_node_300i.md:38 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/single_node_300i.md:48 +msgid "Online Inference on NPU" +msgstr "在NPU上进行在线推理" + +#: ../../tutorials/single_node_300i.md:50 +msgid "" +"Run the following script to start the vLLM server on NPU(Qwen3-0.6B:1 card, " +"Qwen2.5-7B-Instruct:2 cards, Pangu-Pro-MoE-72B: 8 cards):" +msgstr "" +"运行以下脚本，在 NPU 上启动 vLLM 服务器（Qwen3-0.6B：1 张卡，Qwen2.5-7B-Instruct：2 张卡，Pangu-" +"Pro-MoE-72B：8 张卡）：" + +#: ../../tutorials/single_node_300i.md +msgid "Qwen3-0.6B" +msgstr "Qwen3-0.6B" + +#: ../../tutorials/single_node_300i.md:59 +#: ../../tutorials/single_node_300i.md:89 +#: ../../tutorials/single_node_300i.md:126 +msgid "Run the following command to start the vLLM server:" +msgstr "运行以下命令以启动 vLLM 服务器：" + +#: ../../tutorials/single_node_300i.md:70 +#: ../../tutorials/single_node_300i.md:100 +#: ../../tutorials/single_node_300i.md:140 +msgid "" +"Once your server is started, you can query the model with input prompts" +msgstr "一旦服务器启动，就可以通过输入提示词来查询模型。" + +#: ../../tutorials/single_node_300i.md +msgid "Qwen/Qwen2.5-7B-Instruct" +msgstr "Qwen/Qwen2.5-7B-Instruct" + +#: ../../tutorials/single_node_300i.md +msgid "Pangu-Pro-MoE-72B" +msgstr "Pangu-Pro-MoE-72B" + +#: ../../tutorials/single_node_300i.md:119 +#: ../../tutorials/single_node_300i.md:257 +msgid "Download the model:" +msgstr "下载该模型：" + +#: ../../tutorials/single_node_300i.md:157 +msgid "If you run this script successfully, you can see the results." +msgstr "如果你成功运行此脚本，你就可以看到结果。" + +#: ../../tutorials/single_node_300i.md:159 +msgid "Offline Inference" +msgstr "离线推理" + +#: ../../tutorials/single_node_300i.md:161 +msgid "" +"Run the following script (`example.py`) to execute offline inference on NPU:" +msgstr "运行以下脚本（`example.py`）以在 NPU 上执行离线推理：" + +#: ../../tutorials/single_node_300i.md +msgid "Qwen2.5-7B-Instruct" +msgstr "Qwen2.5-7B-指令版" + +#: ../../tutorials/single_node_300i.md:320 +msgid "Run script:" +msgstr "运行脚本：" + +#: ../../tutorials/single_node_300i.md:325 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu.po new file mode 100644 index 000000000..9b69577d6 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu.po @@ -0,0 +1,107 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/single_npu.md:1 +msgid "Single NPU (Qwen3 8B)" +msgstr "单个NPU（Qwen3 8B）" + +#: ../../tutorials/single_npu.md:3 +msgid "Run vllm-ascend on Single NPU" +msgstr "在单个 NPU 上运行 vllm-ascend" + +#: ../../tutorials/single_npu.md:5 +msgid "Offline Inference on Single NPU" +msgstr "在单个NPU上进行离线推理" + +#: ../../tutorials/single_npu.md:7 +msgid "Run docker container:" +msgstr "运行 docker 容器：" + +#: ../../tutorials/single_npu.md:29 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/single_npu.md:40 +msgid "" +"`max_split_size_mb` prevents the native allocator from splitting blocks " +"larger than this size (in MB). This can reduce fragmentation and may allow " +"some borderline workloads to complete without running out of memory. You can" +" find more details " +"[here](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha003/apiref/envref/envref_07_0061.html)." +msgstr "" +"`max_split_size_mb` 防止本地分配器拆分超过此大小（以 MB " +"为单位）的内存块。这可以减少内存碎片，并且可能让一些边缘情况下的工作负载顺利完成而不会耗尽内存。你可以在[这里](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha003/apiref/envref/envref_07_0061.html)找到更多详细信息。" + +#: ../../tutorials/single_npu.md:43 +msgid "Run the following script to execute offline inference on a single NPU:" +msgstr "运行以下脚本以在单个 NPU 上执行离线推理：" + +#: ../../tutorials/single_npu.md +msgid "Graph Mode" +msgstr "图模式" + +#: ../../tutorials/single_npu.md +msgid "Eager Mode" +msgstr "即时模式" + +#: ../../tutorials/single_npu.md:98 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" + +#: ../../tutorials/single_npu.md:105 +msgid "Online Serving on Single NPU" +msgstr "单个 NPU 上的在线服务" + +#: ../../tutorials/single_npu.md:107 +msgid "Run docker container to start the vLLM server on a single NPU:" +msgstr "运行 docker 容器，在单个 NPU 上启动 vLLM 服务器：" + +#: ../../tutorials/single_npu.md:163 +msgid "" +"Add `--max_model_len` option to avoid ValueError that the Qwen2.5-7B model's" +" max seq len (32768) is larger than the maximum number of tokens that can be" +" stored in KV cache (26240). This will differ with different NPU series base" +" on the HBM size. Please modify the value according to a suitable value for " +"your NPU series." +msgstr "" +"添加 `--max_model_len` 选项，以避免出现 Qwen2.5-7B 模型的最大序列长度（32768）大于 KV 缓存能存储的最大 " +"token 数（26240）时的 ValueError。不同 NPU 系列由于 HBM 容量不同，该值也会有所不同。请根据您的 NPU " +"系列，修改为合适的数值。" + +#: ../../tutorials/single_npu.md:166 +msgid "If your service start successfully, you can see the info shown below:" +msgstr "如果你的服务启动成功，你会看到如下所示的信息：" + +#: ../../tutorials/single_npu.md:174 +msgid "" +"Once your server is started, you can query the model with input prompts:" +msgstr "一旦你的服务器启动，你可以通过输入提示词来查询模型：" + +#: ../../tutorials/single_npu.md:187 +msgid "" +"If you query the server successfully, you can see the info shown below " +"(client):" +msgstr "如果你成功查询了服务器，你可以看到如下所示的信息（客户端）：" + +#: ../../tutorials/single_npu.md:193 +msgid "Logs of the vllm server:" +msgstr "vllm 服务器的日志：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_audio.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_audio.po new file mode 100644 index 000000000..71bad64dd --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_audio.po @@ -0,0 +1,77 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/single_npu_audio.md:1 +msgid "Single NPU (Qwen2-Audio 7B)" +msgstr "单个 NPU（Qwen2-Audio 7B）" + +#: ../../tutorials/single_npu_audio.md:3 +msgid "Run vllm-ascend on Single NPU" +msgstr "在单个 NPU 上运行 vllm-ascend" + +#: ../../tutorials/single_npu_audio.md:5 +msgid "Offline Inference on Single NPU" +msgstr "在单个NPU上进行离线推理" + +#: ../../tutorials/single_npu_audio.md:7 +msgid "Run docker container:" +msgstr "运行 docker 容器：" + +#: ../../tutorials/single_npu_audio.md:29 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/single_npu_audio.md:40 +msgid "" +"`max_split_size_mb` prevents the native allocator from splitting blocks " +"larger than this size (in MB). This can reduce fragmentation and may allow " +"some borderline workloads to complete without running out of memory. You can" +" find more details " +"[here](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha003/apiref/envref/envref_07_0061.html)." +msgstr "" +"`max_split_size_mb` 防止本地分配器拆分超过此大小（以 MB " +"为单位）的内存块。这可以减少内存碎片，并且可能让一些边缘情况下的工作负载顺利完成而不会耗尽内存。你可以在[这里](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha003/apiref/envref/envref_07_0061.html)找到更多详细信息。" + +#: ../../tutorials/single_npu_audio.md:43 +msgid "Install packages required for audio processing:" +msgstr "安装音频处理所需的软件包：" + +#: ../../tutorials/single_npu_audio.md:50 +msgid "Run the following script to execute offline inference on a single NPU:" +msgstr "运行以下脚本以在单个 NPU 上执行离线推理：" + +#: ../../tutorials/single_npu_audio.md:114 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" + +#: ../../tutorials/single_npu_audio.md:120 +msgid "Online Serving on Single NPU" +msgstr "单个 NPU 上的在线服务" + +#: ../../tutorials/single_npu_audio.md:122 +msgid "" +"Currently, vllm's OpenAI-compatible server doesn't support audio inputs, " +"find more details [here](https://github.com/vllm-" +"project/vllm/issues/19977)." +msgstr "" +"目前，vllm 的兼容 OpenAI 的服务器不支持音频输入，更多详情请查看[这里](https://github.com/vllm-" +"project/vllm/issues/19977)。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_multimodal.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_multimodal.po new file mode 100644 index 000000000..0007af082 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_multimodal.po @@ -0,0 +1,99 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/single_npu_multimodal.md:1 +msgid "Single NPU (Qwen2.5-VL 7B)" +msgstr "单个NPU（Qwen2.5-VL 7B）" + +#: ../../tutorials/single_npu_multimodal.md:3 +msgid "Run vllm-ascend on Single NPU" +msgstr "在单个 NPU 上运行 vllm-ascend" + +#: ../../tutorials/single_npu_multimodal.md:5 +msgid "Offline Inference on Single NPU" +msgstr "在单个NPU上进行离线推理" + +#: ../../tutorials/single_npu_multimodal.md:7 +msgid "Run docker container:" +msgstr "运行 docker 容器：" + +#: ../../tutorials/single_npu_multimodal.md:29 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/single_npu_multimodal.md:40 +msgid "" +"`max_split_size_mb` prevents the native allocator from splitting blocks " +"larger than this size (in MB). This can reduce fragmentation and may allow " +"some borderline workloads to complete without running out of memory. You can" +" find more details " +"[here](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha003/apiref/envref/envref_07_0061.html)." +msgstr "" +"`max_split_size_mb` 防止本地分配器拆分超过此大小（以 MB " +"为单位）的内存块。这可以减少内存碎片，并且可能让一些边缘情况下的工作负载顺利完成而不会耗尽内存。你可以在[这里](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/800alpha003/apiref/envref/envref_07_0061.html)找到更多详细信息。" + +#: ../../tutorials/single_npu_multimodal.md:43 +msgid "Run the following script to execute offline inference on a single NPU:" +msgstr "运行以下脚本以在单个 NPU 上执行离线推理：" + +#: ../../tutorials/single_npu_multimodal.md:109 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" + +#: ../../tutorials/single_npu_multimodal.md:121 +msgid "Online Serving on Single NPU" +msgstr "单个 NPU 上的在线服务" + +#: ../../tutorials/single_npu_multimodal.md:123 +msgid "Run docker container to start the vLLM server on a single NPU:" +msgstr "运行 docker 容器，在单个 NPU 上启动 vLLM 服务器：" + +#: ../../tutorials/single_npu_multimodal.md:154 +msgid "" +"Add `--max_model_len` option to avoid ValueError that the " +"Qwen2.5-VL-7B-Instruct model's max seq len (128000) is larger than the " +"maximum number of tokens that can be stored in KV cache. This will differ " +"with different NPU series base on the HBM size. Please modify the value " +"according to a suitable value for your NPU series." +msgstr "" +"新增 `--max_model_len` 选项，以避免出现 ValueError，即 Qwen2.5-VL-7B-Instruct " +"模型的最大序列长度（128000）大于 KV 缓存可存储的最大 token 数。该数值会根据不同 NPU 系列的 HBM 大小而不同。请根据你的 NPU" +" 系列，将该值设置为合适的数值。" + +#: ../../tutorials/single_npu_multimodal.md:157 +msgid "If your service start successfully, you can see the info shown below:" +msgstr "如果你的服务启动成功，你会看到如下所示的信息：" + +#: ../../tutorials/single_npu_multimodal.md:165 +msgid "" +"Once your server is started, you can query the model with input prompts:" +msgstr "一旦你的服务器启动，你可以通过输入提示词来查询模型：" + +#: ../../tutorials/single_npu_multimodal.md:182 +msgid "" +"If you query the server successfully, you can see the info shown below " +"(client):" +msgstr "如果你成功查询了服务器，你可以看到如下所示的信息（客户端）：" + +#: ../../tutorials/single_npu_multimodal.md:188 +msgid "Logs of the vllm server:" +msgstr "vllm 服务器的日志：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_qwen3_embedding.po b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_qwen3_embedding.po new file mode 100644 index 000000000..4eb349a8a --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/tutorials/single_npu_qwen3_embedding.po @@ -0,0 +1,70 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../tutorials/single_npu_qwen3_embedding.md:1 +msgid "Single NPU (Qwen3-Embedding-8B)" +msgstr "单个NPU（Qwen3-Embedding-8B）" + +#: ../../tutorials/single_npu_qwen3_embedding.md:3 +msgid "" +"The Qwen3 Embedding model series is the latest proprietary model of the Qwen" +" family, specifically designed for text embedding and ranking tasks. " +"Building upon the dense foundational models of the Qwen3 series, it provides" +" a comprehensive range of text embeddings and reranking models in various " +"sizes (0.6B, 4B, and 8B). This guide describes how to run the model with " +"vLLM Ascend. Note that only 0.9.2rc1 and higher versions of vLLM Ascend " +"support the model." +msgstr "" +"Qwen3 Embedding 模型系列是 Qwen 家族最新的专有模型，专为文本嵌入和排序任务设计。在 Qwen3 " +"系列的密集基础模型之上，它提供了多种尺寸（0.6B、4B 和 8B）的文本嵌入与重排序模型。本指南介绍如何使用 vLLM Ascend " +"运行该模型。请注意，只有 vLLM Ascend 0.9.2rc1 及更高版本才支持该模型。" + +#: ../../tutorials/single_npu_qwen3_embedding.md:5 +msgid "Run docker container" +msgstr "运行 docker 容器" + +#: ../../tutorials/single_npu_qwen3_embedding.md:7 +msgid "" +"Take Qwen3-Embedding-8B model as an example, first run the docker container " +"with the following command:" +msgstr "以 Qwen3-Embedding-8B 模型为例，首先使用以下命令运行 docker 容器：" + +#: ../../tutorials/single_npu_qwen3_embedding.md:29 +msgid "Setup environment variables:" +msgstr "设置环境变量：" + +#: ../../tutorials/single_npu_qwen3_embedding.md:39 +msgid "Online Inference" +msgstr "在线推理" + +#: ../../tutorials/single_npu_qwen3_embedding.md:45 +msgid "" +"Once your server is started, you can query the model with input prompts" +msgstr "一旦服务器启动，就可以通过输入提示词来查询模型。" + +#: ../../tutorials/single_npu_qwen3_embedding.md:56 +msgid "Offline Inference" +msgstr "离线推理" + +#: ../../tutorials/single_npu_qwen3_embedding.md:92 +msgid "If you run this script successfully, you can see the info shown below:" +msgstr "如果你成功运行此脚本，你可以看到如下所示的信息：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/additional_config.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/additional_config.po new file mode 100644 index 000000000..54dacd65f --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/additional_config.po @@ -0,0 +1,290 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/configuration/additional_config.md:1 +msgid "Additional Configuration" +msgstr "附加配置" + +#: ../../user_guide/configuration/additional_config.md:3 +msgid "" +"additional configuration is a mechanism provided by vLLM to allow plugins to" +" control inner behavior by their own. vLLM Ascend uses this mechanism to " +"make the project more flexible." +msgstr "额外配置是 vLLM 提供的一种机制，允许插件自行控制内部行为。vLLM Ascend 利用这种机制使项目更加灵活。" + +#: ../../user_guide/configuration/additional_config.md:5 +msgid "How to use" +msgstr "如何使用" + +#: ../../user_guide/configuration/additional_config.md:7 +msgid "" +"With either online mode or offline mode, users can use additional " +"configuration. Take Qwen3 as an example:" +msgstr "无论是在线模式还是离线模式，用户都可以使用额外的配置。以 Qwen3 为例：" + +#: ../../user_guide/configuration/additional_config.md:9 +msgid "**Online mode**:" +msgstr "**在线模式**：" + +#: ../../user_guide/configuration/additional_config.md:15 +msgid "**Offline mode**:" +msgstr "**离线模式**：" + +#: ../../user_guide/configuration/additional_config.md:23 +msgid "Configuration options" +msgstr "配置选项" + +#: ../../user_guide/configuration/additional_config.md:25 +msgid "" +"The following table lists the additional configuration options available in " +"vLLM Ascend:" +msgstr "下表列出了 vLLM Ascend 中可用的其他配置选项：" + +#: ../../user_guide/configuration/additional_config.md +msgid "Name" +msgstr "名称" + +#: ../../user_guide/configuration/additional_config.md +msgid "Type" +msgstr "类型" + +#: ../../user_guide/configuration/additional_config.md +msgid "Default" +msgstr "默认" + +#: ../../user_guide/configuration/additional_config.md +msgid "Description" +msgstr "描述" + +#: ../../user_guide/configuration/additional_config.md +msgid "`torchair_graph_config`" +msgstr "`torchair_graph_config`" + +#: ../../user_guide/configuration/additional_config.md +msgid "dict" +msgstr "dict" + +#: ../../user_guide/configuration/additional_config.md +#, python-brace-format +msgid "`{}`" +msgstr "`{}`" + +#: ../../user_guide/configuration/additional_config.md +msgid "The config options for torchair graph mode" +msgstr "torchair 图模式的配置选项" + +#: ../../user_guide/configuration/additional_config.md +msgid "`ascend_scheduler_config`" +msgstr "`ascend_scheduler_config`" + +#: ../../user_guide/configuration/additional_config.md +msgid "The config options for ascend scheduler" +msgstr "ascend 调度器的配置选项" + +#: ../../user_guide/configuration/additional_config.md +msgid "`expert_tensor_parallel_size`" +msgstr "`expert_tensor_parallel_size`" + +#: ../../user_guide/configuration/additional_config.md +msgid "str" +msgstr "str" + +#: ../../user_guide/configuration/additional_config.md +msgid "`0`" +msgstr "`0`" + +#: ../../user_guide/configuration/additional_config.md +msgid "Expert tensor parallel size the model to use." +msgstr "专家张量并行的模型大小设置。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`refresh`" +msgstr "`刷新`" + +#: ../../user_guide/configuration/additional_config.md +msgid "bool" +msgstr "bool" + +#: ../../user_guide/configuration/additional_config.md +msgid "`false`" +msgstr "`false`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"Whether to refresh global ascend config content. This value is usually used " +"by rlhf or ut/e2e test case." +msgstr "是否刷新全局 ascend 配置信息。此值通常由 rlhf 或 ut/e2e 测试用例使用。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`expert_map_path`" +msgstr "`expert_map_path`" + +#: ../../user_guide/configuration/additional_config.md +msgid "`None`" +msgstr "`None`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"When using expert load balancing for the MOE model, an expert map path needs" +" to be passed in." +msgstr "在为MOE模型使用专家负载均衡时，需要传入专家映射路径。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`chunked_prefill_for_mla`" +msgstr "`chunked_prefill_for_mla`" + +#: ../../user_guide/configuration/additional_config.md +msgid "`False`" +msgstr "`False`" + +#: ../../user_guide/configuration/additional_config.md +msgid "Whether to enable the fused operator-like chunked_prefill." +msgstr "是否启用类似算子融合的 chunked_prefill 功能。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`kv_cache_dtype`" +msgstr "`kv_cache_dtype`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"When using the kv cache quantization method, kv cache dtype needs to be set," +" currently only int8 is supported." +msgstr "当使用kv缓存量化方法时，需要设置kv缓存的数据类型，目前仅支持int8。" + +#: ../../user_guide/configuration/additional_config.md:37 +msgid "The details of each config option are as follows:" +msgstr "每个配置选项的详细信息如下：" + +#: ../../user_guide/configuration/additional_config.md:39 +msgid "**torchair_graph_config**" +msgstr "**torchair_graph_config**" + +#: ../../user_guide/configuration/additional_config.md +msgid "`enabled`" +msgstr "`启用`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"Whether to enable torchair graph mode. Currently only DeepSeek series models" +" and PanguProMoE are supported to use torchair graph mode" +msgstr "是否启用 torchair 图模式。目前仅支持 DeepSeek 系列模型和 PanguProMoE 使用 torchair 图模式。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`enable_multistream_mla`" +msgstr "`enable_multistream_mla`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"Whether to put vector ops of MLA to another stream. This option only takes " +"effects on models using MLA (e.g., DeepSeek)." +msgstr "是否将MLA的向量操作放到另一个流中。此选项仅对使用MLA的模型（例如，DeepSeek）有效。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`enable_multistream_moe`" +msgstr "`enable_multistream_moe`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"Whether to enable multistream shared expert. This option only takes effects " +"on DeepSeek moe models." +msgstr "是否启用多流共享专家功能。此选项仅对 DeepSeek MoE 模型生效。" + +#: ../../user_guide/configuration/additional_config.md +msgid "`enable_view_optimize`" +msgstr "`enable_view_optimize` （启用视图优化）" + +#: ../../user_guide/configuration/additional_config.md +msgid "`True`" +msgstr "`True`" + +#: ../../user_guide/configuration/additional_config.md +msgid "Whether to enable torchair view optimization" +msgstr "是否启用torchair视图优化" + +#: ../../user_guide/configuration/additional_config.md +msgid "`use_cached_graph`" +msgstr "`use_cached_graph`" + +#: ../../user_guide/configuration/additional_config.md +msgid "Whether to use cached graph" +msgstr "是否使用缓存的图" + +#: ../../user_guide/configuration/additional_config.md +msgid "`graph_batch_sizes`" +msgstr "`graph_batch_sizes`" + +#: ../../user_guide/configuration/additional_config.md +msgid "list[int]" +msgstr "list[int]" + +#: ../../user_guide/configuration/additional_config.md +msgid "`[]`" +msgstr "`[]`" + +#: ../../user_guide/configuration/additional_config.md +msgid "The batch size for torchair graph cache" +msgstr "torchair 图缓存的批量大小" + +#: ../../user_guide/configuration/additional_config.md +msgid "`graph_batch_sizes_init`" +msgstr "`graph_batch_sizes_init`" + +#: ../../user_guide/configuration/additional_config.md +msgid "Init graph batch size dynamically if `graph_batch_sizes` is empty" +msgstr "如果 `graph_batch_sizes` 为空，则动态初始化图批大小" + +#: ../../user_guide/configuration/additional_config.md +msgid "`enable_kv_nz`" +msgstr "`enable_kv_nz`" + +#: ../../user_guide/configuration/additional_config.md +msgid "" +"Whether to enable kvcache NZ layout. This option only takes effects on " +"models using MLA (e.g., DeepSeek)." +msgstr "是否启用 kvcache NZ 布局。此选项仅对使用 MLA 的模型（例如 DeepSeek）生效。" + +#: ../../user_guide/configuration/additional_config.md:52 +msgid "**ascend_scheduler_config**" +msgstr "**ascend_scheduler_config**" + +#: ../../user_guide/configuration/additional_config.md +msgid "Whether to enable ascend scheduler for V1 engine" +msgstr "是否为 V1 引擎启用 ascend 调度器" + +#: ../../user_guide/configuration/additional_config.md:58 +msgid "" +"ascend_scheduler_config also support the options from [vllm scheduler " +"config](https://docs.vllm.ai/en/stable/api/vllm/config.html#vllm.config.SchedulerConfig)." +" For example, you can add `enable_chunked_prefill: True` to " +"ascend_scheduler_config as well." +msgstr "" +"ascend_scheduler_config 也支持来自 [vllm scheduler " +"config](https://docs.vllm.ai/en/stable/api/vllm/config.html#vllm.config.SchedulerConfig)" +" 的选项。例如，你也可以在 ascend_scheduler_config 中添加 `enable_chunked_prefill: True`。" + +#: ../../user_guide/configuration/additional_config.md:60 +msgid "Example" +msgstr "示例" + +#: ../../user_guide/configuration/additional_config.md:62 +msgid "An example of additional configuration is as follows:" +msgstr "以下是额外配置的一个示例：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/env_vars.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/env_vars.po new file mode 100644 index 000000000..769efa26d --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/env_vars.po @@ -0,0 +1,28 @@ +# Translations template for PROJECT. +# Copyright (C) 2025 ORGANIZATION +# This file is distributed under the same license as the PROJECT project. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: PROJECT VERSION\n" +"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: LANGUAGE \n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/configuration/env_vars.md:1 +msgid "Environment Variables" +msgstr "环境变量" + +#: ../../user_guide/configuration/env_vars.md:3 +msgid "" +"vllm-ascend uses the following environment variables to configure the " +"system:" +msgstr "vllm-ascend 使用以下环境变量来配置系统：" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/index.po new file mode 100644 index 000000000..2c5f79020 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/index.po @@ -0,0 +1,30 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/configuration/index.md:1 +#: ../../user_guide/configuration/index.md:5 +msgid "Configuration Guide" +msgstr "配置指南" + +#: ../../user_guide/configuration/index.md:3 +msgid "This section provides a detailed configuration guide of vLLM Ascend." +msgstr "本节提供了 vLLM Ascend 的详细配置指南。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/graph_mode.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/graph_mode.po new file mode 100644 index 000000000..9680bdbe6 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/graph_mode.po @@ -0,0 +1,121 @@ +# Translations template for PROJECT. +# Copyright (C) 2025 ORGANIZATION +# This file is distributed under the same license as the PROJECT project. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: PROJECT VERSION\n" +"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: LANGUAGE \n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/feature_guide/graph_mode.md:1 +msgid "Graph Mode Guide" +msgstr "图模式指南" + +#: ../../user_guide/feature_guide/graph_mode.md:4 +msgid "" +"This feature is currently experimental. In future versions, there may be " +"behavioral changes around configuration, coverage, performance improvement." +msgstr "此功能目前为实验性功能。在未来的版本中，配置、覆盖率和性能改进等方面的行为可能会有变化。" + +#: ../../user_guide/feature_guide/graph_mode.md:7 +msgid "" +"This guide provides instructions for using Ascend Graph Mode with vLLM " +"Ascend. Please note that graph mode is only available on V1 Engine. And only" +" Qwen, DeepSeek series models are well tested from 0.9.0rc1. We'll make it " +"stable and generalize in the next release." +msgstr "" +"本指南提供了在 vLLM Ascend 上使用 Ascend 图模式的操作说明。请注意，图模式仅在 V1 引擎上可用，并且从 0.9.0rc1 起，仅对" +" Qwen、DeepSeek 系列模型进行了充分测试。我们将在下一个版本中使其更加稳定和通用。" + +#: ../../user_guide/feature_guide/graph_mode.md:9 +msgid "Getting Started" +msgstr "快速入门" + +#: ../../user_guide/feature_guide/graph_mode.md:11 +msgid "" +"From v0.9.1rc1 with V1 Engine, vLLM Ascend will run models in graph mode by " +"default to keep the same behavior with vLLM. If you hit any issues, please " +"feel free to open an issue on GitHub and fallback to eager mode temporarily " +"by set `enforce_eager=True` when initializing the model." +msgstr "" +"从 v0.9.1rc1 版本起，使用 V1 引擎时，vLLM Ascend 默认将在图模式下运行模型，以保持与 vLLM " +"同样的行为。如果遇到任何问题，欢迎在 GitHub 上提交 issue，并在初始化模型时通过设置 `enforce_eager=True` 临时切换回 " +"eager 模式。" + +#: ../../user_guide/feature_guide/graph_mode.md:13 +msgid "There are two kinds for graph mode supported by vLLM Ascend:" +msgstr "vLLM Ascend 支持两种图模式：" + +#: ../../user_guide/feature_guide/graph_mode.md:14 +msgid "" +"**ACLGraph**: This is the default graph mode supported by vLLM Ascend. In " +"v0.9.1rc1, only Qwen series models are well tested." +msgstr "" +"**ACLGraph**：这是 vLLM Ascend 支持的默认图模式。在 v0.9.1rc1 版本中，只有 Qwen 系列模型得到了充分测试。" + +#: ../../user_guide/feature_guide/graph_mode.md:15 +msgid "" +"**TorchAirGraph**: This is the GE graph mode. In v0.9.1rc1, only DeepSeek " +"series models are supported." +msgstr "**TorchAirGraph**：这是GE图模式。在v0.9.1rc1版本中，仅支持DeepSeek系列模型。" + +#: ../../user_guide/feature_guide/graph_mode.md:17 +msgid "Using ACLGraph" +msgstr "使用 ACLGraph" + +#: ../../user_guide/feature_guide/graph_mode.md:18 +msgid "" +"ACLGraph is enabled by default. Take Qwen series models as an example, just " +"set to use V1 Engine is enough." +msgstr "ACLGraph 默认启用。以 Qwen 系列模型为例，只需设置为使用 V1 引擎即可。" + +#: ../../user_guide/feature_guide/graph_mode.md:20 +#: ../../user_guide/feature_guide/graph_mode.md:41 +#: ../../user_guide/feature_guide/graph_mode.md:64 +msgid "offline example:" +msgstr "离线示例：" + +#: ../../user_guide/feature_guide/graph_mode.md:31 +#: ../../user_guide/feature_guide/graph_mode.md:52 +#: ../../user_guide/feature_guide/graph_mode.md:74 +msgid "online example:" +msgstr "在线示例：" + +#: ../../user_guide/feature_guide/graph_mode.md:37 +msgid "Using TorchAirGraph" +msgstr "使用 TorchAirGraph" + +#: ../../user_guide/feature_guide/graph_mode.md:39 +msgid "" +"If you want to run DeepSeek series models with graph mode, you should use " +"[TorchAirGraph](https://www.hiascend.com/document/detail/zh/Pytorch/700/modthirdparty/torchairuseguide/torchair_0002.html)." +" In this case, additional config is required." +msgstr "" +"如果你想通过图模式运行 DeepSeek 系列模型，你应该使用 " +"[TorchAirGraph](https://www.hiascend.com/document/detail/zh/Pytorch/700/modthirdparty/torchairuseguide/torchair_0002.html)。在这种情况下，需要额外的配置。" + +#: ../../user_guide/feature_guide/graph_mode.md:58 +msgid "" +"You can find more detail about additional config " +"[here](../configuration/additional_config.md)." +msgstr "你可以在[这里](../configuration/additional_config.md)找到关于附加配置的更多详细信息。" + +#: ../../user_guide/feature_guide/graph_mode.md:60 +msgid "Fallback to Eager Mode" +msgstr "回退到 Eager 模式" + +#: ../../user_guide/feature_guide/graph_mode.md:62 +msgid "" +"If both `ACLGraph` and `TorchAirGraph` fail to run, you should fallback to " +"eager mode." +msgstr "如果 `ACLGraph` 和 `TorchAirGraph` 都无法运行，你应该退回到 eager 模式。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/index.po new file mode 100644 index 000000000..624c39f27 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/index.po @@ -0,0 +1,30 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/feature_guide/index.md:1 +#: ../../user_guide/feature_guide/index.md:5 +msgid "Feature Guide" +msgstr "功能指南" + +#: ../../user_guide/feature_guide/index.md:3 +msgid "This section provides a detailed usage guide of vLLM Ascend features." +msgstr "本节提供了 vLLM Ascend 功能的详细使用指南。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/lora.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/lora.po new file mode 100644 index 000000000..957ec1735 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/lora.po @@ -0,0 +1,58 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/feature_guide/lora.md:1 +msgid "LoRA Adapters Guide" +msgstr "LoRA 适配器指南" + +#: ../../user_guide/feature_guide/lora.md:3 +msgid "" +"Like vLLM, vllm-ascend supports LoRA as well. The usage and more details can" +" be found in [vLLM official " +"document](https://docs.vllm.ai/en/latest/features/lora.html)." +msgstr "" +"与 vLLM 类似，vllm-ascend 也支持 LoRA。用法及更多详情可参见 [vLLM " +"官方文档](https://docs.vllm.ai/en/latest/features/lora.html)。" + +#: ../../user_guide/feature_guide/lora.md:5 +msgid "" +"You can also refer to " +"[this](https://docs.vllm.ai/en/latest/models/supported_models.html#list-of-" +"text-only-language-models) to find which models support LoRA in vLLM." +msgstr "" +"你也可以参考[这个链接](https://docs.vllm.ai/en/latest/models/supported_models.html#list-" +"of-text-only-language-models)来查找哪些模型在 vLLM 中支持 LoRA。" + +#: ../../user_guide/feature_guide/lora.md:7 +msgid "Tips" +msgstr "提示" + +#: ../../user_guide/feature_guide/lora.md:8 +msgid "" +"If you fail to run vllm-ascend with LoRA, you may follow [this " +"instruction](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/feature_guide/graph_mode.html#fallback-" +"to-eager-mode) to disable graph mode and try again." +msgstr "" +"如果你在使用 LoRA 运行 vllm-ascend 时失败，可以按照[此说明](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/feature_guide/graph_mode.html#fallback-" +"to-eager-mode)禁用图模式后再重试。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/quantization.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/quantization.po new file mode 100644 index 000000000..54f524e3a --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/quantization.po @@ -0,0 +1,183 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/feature_guide/quantization.md:1 +msgid "Quantization Guide" +msgstr "量化指南" + +#: ../../user_guide/feature_guide/quantization.md:3 +msgid "" +"Model quantization is a technique that reduces the size and computational " +"requirements of a model by lowering the data precision of the weights and " +"activation values in the model, thereby saving the memory and improving the " +"inference speed." +msgstr "模型量化是一种通过降低模型中权重和激活值的数据精度，从而减少模型大小和计算需求的技术，这样可以节省内存并提高推理速度。" + +#: ../../user_guide/feature_guide/quantization.md:5 +msgid "" +"Since 0.9.0rc2 version, quantization feature is experimentally supported in " +"vLLM Ascend. Users can enable quantization feature by specifying " +"`--quantization ascend`. Currently, only Qwen, DeepSeek series models are " +"well tested. We’ll support more quantization algorithm and models in the " +"future." +msgstr "" +"自 0.9.0rc2 版本起，vLLM Ascend 实验性地支持量化特性。用户可以通过指定 `--quantization ascend` " +"启用量化功能。目前，只有 Qwen、DeepSeek 系列模型经过了充分测试。未来我们将支持更多的量化算法和模型。" + +#: ../../user_guide/feature_guide/quantization.md:7 +msgid "Install modelslim" +msgstr "安装 modelslim" + +#: ../../user_guide/feature_guide/quantization.md:9 +msgid "" +"To quantize a model, users should install " +"[ModelSlim](https://gitee.com/ascend/msit/blob/master/msmodelslim/README.md)" +" which is the Ascend compression and acceleration tool. It is an affinity-" +"based compression tool designed for acceleration, using compression as its " +"core technology and built upon the Ascend platform." +msgstr "" +"要对模型进行量化，用户应安装[ModelSlim](https://gitee.com/ascend/msit/blob/master/msmodelslim/README.md)，这是昇腾的压缩与加速工具。它是一种基于亲和性的压缩工具，专为加速设计，以压缩为核心技术，并基于昇腾平台构建。" + +#: ../../user_guide/feature_guide/quantization.md:11 +msgid "" +"Currently, only the specific tag [modelslim-" +"VLLM-8.1.RC1.b020_001](https://gitee.com/ascend/msit/blob/modelslim-" +"VLLM-8.1.RC1.b020_001/msmodelslim/README.md) of modelslim works with vLLM " +"Ascend. Please do not install other version until modelslim master version " +"is available for vLLM Ascend in the future." +msgstr "" +"目前，只有 modelslim 的特定标签 [modelslim-" +"VLLM-8.1.RC1.b020_001](https://gitee.com/ascend/msit/blob/modelslim-" +"VLLM-8.1.RC1.b020_001/msmodelslim/README.md) 支持 vLLM Ascend。在未来 modelslim " +"的主版本支持 vLLM Ascend 之前，请不要安装其他版本。" + +#: ../../user_guide/feature_guide/quantization.md:13 +msgid "Install modelslim:" +msgstr "安装 modelslim：" + +#: ../../user_guide/feature_guide/quantization.md:21 +msgid "Quantize model" +msgstr "量化模型" + +#: ../../user_guide/feature_guide/quantization.md:23 +#, python-format +msgid "" +"Take [DeepSeek-V2-Lite](https://modelscope.cn/models/deepseek-" +"ai/DeepSeek-V2-Lite) as an example, you just need to download the model, and" +" then execute the convert command. The command is shown below. More info can" +" be found in modelslim doc [deepseek w8a8 dynamic quantization " +"docs](https://gitee.com/ascend/msit/blob/modelslim-" +"VLLM-8.1.RC1.b020_001/msmodelslim/example/DeepSeek/README.md#deepseek-v2-w8a8-dynamic%E9%87%8F%E5%8C%96)." +msgstr "" +"以 [DeepSeek-V2-Lite](https://modelscope.cn/models/deepseek-" +"ai/DeepSeek-V2-Lite) 为例，你只需要下载模型，然后执行转换命令。命令如下所示。更多信息可参考 modelslim 文档 " +"[deepseek w8a8 动态量化文档](https://gitee.com/ascend/msit/blob/modelslim-" +"VLLM-8.1.RC1.b020_001/msmodelslim/example/DeepSeek/README.md#deepseek-v2-w8a8-dynamic%E9%87%8F%E5%8C%96)。" + +#: ../../user_guide/feature_guide/quantization.md:32 +msgid "" +"You can also download the quantized model that we uploaded. Please note that" +" these weights should be used for test only. For example, " +"https://www.modelscope.cn/models/vllm-ascend/DeepSeek-V2-Lite-W8A8" +msgstr "" +"你也可以下载我们上传的量化模型。请注意，这些权重仅应用于测试。例如：https://www.modelscope.cn/models/vllm-" +"ascend/DeepSeek-V2-Lite-W8A8" + +#: ../../user_guide/feature_guide/quantization.md:35 +msgid "Once convert action is done, there are two important files generated." +msgstr "转换操作完成后，会生成两个重要的文件。" + +#: ../../user_guide/feature_guide/quantization.md:37 +msgid "" +"[config.json](https://www.modelscope.cn/models/vllm-" +"ascend/DeepSeek-V2-Lite-W8A8/file/view/master/config.json?status=1). Please " +"make sure that there is no `quantization_config` field in it." +msgstr "" +"[config.json](https://www.modelscope.cn/models/vllm-" +"ascend/DeepSeek-V2-Lite-W8A8/file/view/master/config.json?status=1)。请确保其中没有 " +"`quantization_config` 字段。" + +#: ../../user_guide/feature_guide/quantization.md:39 +msgid "" +"[quant_model_description.json](https://www.modelscope.cn/models/vllm-" +"ascend/DeepSeek-V2-Lite-W8A8/file/view/master/quant_model_description.json?status=1)." +" All the converted weights info are recorded in this file." +msgstr "" +"[quant_model_description.json](https://www.modelscope.cn/models/vllm-" +"ascend/DeepSeek-V2-Lite-W8A8/file/view/master/quant_model_description.json?status=1)。所有被转换的权重信息都记录在该文件中。" + +#: ../../user_guide/feature_guide/quantization.md:41 +msgid "Here is the full converted model files:" +msgstr "以下是完整转换后的模型文件：" + +#: ../../user_guide/feature_guide/quantization.md:60 +msgid "Run the model" +msgstr "运行模型" + +#: ../../user_guide/feature_guide/quantization.md:62 +msgid "" +"Now, you can run the quantized models with vLLM Ascend. Here is the example " +"for online and offline inference." +msgstr "现在，你可以使用 vLLM Ascend 运行量化模型。下面是在线和离线推理的示例。" + +#: ../../user_guide/feature_guide/quantization.md:64 +msgid "Offline inference" +msgstr "离线推理" + +#: ../../user_guide/feature_guide/quantization.md:90 +msgid "Online inference" +msgstr "在线推理" + +#: ../../user_guide/feature_guide/quantization.md:97 +msgid "FAQs" +msgstr "常见问题解答" + +#: ../../user_guide/feature_guide/quantization.md:99 +msgid "" +"1. How to solve the KeyError: 'xxx.layers.0.self_attn.q_proj.weight' " +"problem?" +msgstr "1. 如何解决 KeyError: 'xxx.layers.0.self_attn.q_proj.weight' 问题？" + +#: ../../user_guide/feature_guide/quantization.md:101 +msgid "" +"First, make sure you specify `ascend` quantization method. Second, check if " +"your model is converted by this `modelslim-VLLM-8.1.RC1.b020_001` modelslim " +"version. Finally, if it still doesn't work, please submit a issue, maybe " +"some new models need to be adapted." +msgstr "" +"首先，请确保你指定了 `ascend` 量化方法。其次，检查你的模型是否由 `modelslim-VLLM-8.1.RC1.b020_001` 这个 " +"modelslim 版本转换。如果仍然无法使用，请提交一个 issue，可能有一些新模型需要适配。" + +#: ../../user_guide/feature_guide/quantization.md:104 +msgid "" +"2. How to solve the error \"Could not locate the " +"configuration_deepseek.py\"?" +msgstr "2. 如何解决“无法找到 configuration_deepseek.py”错误？" + +#: ../../user_guide/feature_guide/quantization.md:106 +msgid "" +"Please convert DeepSeek series models using `modelslim-" +"VLLM-8.1.RC1.b020_001` modelslim, this version has fixed the missing " +"configuration_deepseek.py error." +msgstr "" +"请使用 `modelslim-VLLM-8.1.RC1.b020_001` 的 modelslim 转换 DeepSeek 系列模型，该版本已修复缺少 " +"configuration_deepseek.py 的错误。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/sleep_mode.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/sleep_mode.po new file mode 100644 index 000000000..a3bd1b214 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/sleep_mode.po @@ -0,0 +1,156 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/feature_guide/sleep_mode.md:1 +msgid "Sleep Mode Guide" +msgstr "睡眠模式指南" + +#: ../../user_guide/feature_guide/sleep_mode.md:3 +msgid "Overview" +msgstr "概述" + +#: ../../user_guide/feature_guide/sleep_mode.md:5 +msgid "" +"Sleep Mode is an API designed to offload model weights and discard KV cache " +"from NPU memory. This functionality is essential for reinforcement learning " +"(RL) post-training workloads, particularly in online algorithms such as PPO," +" GRPO, or DPO. During training, the policy model typically performs auto-" +"regressive generation using inference engines like vLLM, followed by forward" +" and backward passes for optimization." +msgstr "" +"Sleep Mode 是一个用于卸载模型权重并清除 NPU 内存中 KV 缓存的 API。此功能对于强化学习（RL）后训练任务尤其重要，特别是在 " +"PPO、GRPO 或 DPO 等在线算法中。在训练过程中，策略模型通常会使用像 vLLM " +"这样的推理引擎进行自回归生成，然后进行前向和反向传播以进行优化。" + +#: ../../user_guide/feature_guide/sleep_mode.md:7 +msgid "" +"Since the generation and training phases may employ different model " +"parallelism strategies, it becomes crucial to free KV cache and even offload" +" model parameters stored within vLLM during training. This ensures efficient" +" memory utilization and avoids resource contention on the NPU." +msgstr "" +"由于生成和训练阶段可能采用不同的模型并行策略，因此在训练过程中及时释放 KV 缓存，甚至卸载存储在 vLLM " +"内的模型参数变得至关重要。这可以确保内存的高效利用，并避免 NPU 上的资源争用。" + +#: ../../user_guide/feature_guide/sleep_mode.md:10 +msgid "Getting started" +msgstr "快速上手" + +#: ../../user_guide/feature_guide/sleep_mode.md:12 +#, python-brace-format +msgid "" +"With `enable_sleep_mode=True`, the way we manage memory(malloc, free) in " +"vllm will under a specific memory pool, during loading model and initialize " +"kv_caches, we tag the memory as a map: `{\"weight\": data, \"kv_cache\": " +"data}`." +msgstr "" +"当 `enable_sleep_mode=True` 时，我们在 vllm 中管理内存（malloc, " +"free）的方式会在一个特定的内存池下进行，在加载模型和初始化 kv_caches " +"期间，我们会将内存打上标签，组织成一个映射：`{\"weight\": data, \"kv_cache\": data}`。" + +#: ../../user_guide/feature_guide/sleep_mode.md:14 +msgid "" +"The engine(v0/v1) supports two sleep levels to manage memory during idle " +"periods:" +msgstr "该引擎（v0/v1）支持两种睡眠等级，以在空闲期间管理内存：" + +#: ../../user_guide/feature_guide/sleep_mode.md:16 +msgid "Level 1 Sleep" +msgstr "一级睡眠" + +#: ../../user_guide/feature_guide/sleep_mode.md:17 +msgid "Action: Offloads model weights and discards the KV cache." +msgstr "操作：卸载模型权重并清除KV缓存。" + +#: ../../user_guide/feature_guide/sleep_mode.md:18 +msgid "Memory: Model weights are moved to CPU memory; KV cache is forgotten." +msgstr "内存：模型权重被移动到CPU内存；KV缓存被清除。" + +#: ../../user_guide/feature_guide/sleep_mode.md:19 +msgid "Use Case: Suitable when reusing the same model later." +msgstr "用例：适用于之后需要重复使用同一个模型的情况。" + +#: ../../user_guide/feature_guide/sleep_mode.md:20 +msgid "" +"Note: Ensure sufficient CPU memory is available to hold the model weights." +msgstr "注意：请确保有足够的CPU内存来存储模型权重。" + +#: ../../user_guide/feature_guide/sleep_mode.md:22 +msgid "Level 2 Sleep" +msgstr "二级睡眠" + +#: ../../user_guide/feature_guide/sleep_mode.md:23 +msgid "Action: Discards both model weights and KV cache." +msgstr "操作：同时丢弃模型权重和KV缓存。" + +#: ../../user_guide/feature_guide/sleep_mode.md:24 +msgid "" +"Memory: The content of both the model weights and kv cache is forgotten." +msgstr "内存：模型权重和kv缓存的内容都会被遗忘。" + +#: ../../user_guide/feature_guide/sleep_mode.md:25 +msgid "" +"Use Case: Ideal when switching to a different model or updating the current " +"one." +msgstr "用例：当切换到不同的模型或更新当前模型时非常理想。" + +#: ../../user_guide/feature_guide/sleep_mode.md:27 +msgid "" +"Since this feature uses the low-level API " +"[AscendCL](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/82RC1alpha002/API/appdevgapi/appdevgapi_07_0000.html)," +" in order to use sleep mode, you should follow the [installation " +"guide](https://vllm-ascend.readthedocs.io/en/latest/installation.html) and " +"building from source, if you are using v0.7.3, remember to set `export " +"COMPILE_CUSTOM_KERNELS=1`, for the latest version(v0.9.x+), the environment " +"variable `COMPILE_CUSTOM_KERNELS` will be set 1 by default while building " +"from source." +msgstr "" +"由于此功能使用了底层 API " +"[AscendCL](https://www.hiascend.com/document/detail/zh/CANNCommunityEdition/82RC1alpha002/API/appdevgapi/appdevgapi_07_0000.html)，为了使用休眠模式，你应按照[安装指南](https://vllm-" +"ascend.readthedocs.io/en/latest/installation.html)进行操作，并从源码编译。如果你使用的是 " +"v0.7.3，请记得设置 `export COMPILE_CUSTOM_KERNELS=1` ；对于最新版本（v0.9.x+），在从源码编译时环境变量 " +"`COMPILE_CUSTOM_KERNELS` 默认会被设置为 1。" + +#: ../../user_guide/feature_guide/sleep_mode.md:29 +msgid "Usage" +msgstr "用法" + +#: ../../user_guide/feature_guide/sleep_mode.md:31 +msgid "The following is a simple example of how to use sleep mode." +msgstr "以下是如何使用睡眠模式的一个简单示例。" + +#: ../../user_guide/feature_guide/sleep_mode.md:33 +msgid "offline inference:" +msgstr "离线推理：" + +#: ../../user_guide/feature_guide/sleep_mode.md:72 +msgid "online serving:" +msgstr "在线服务：" + +#: ../../user_guide/feature_guide/sleep_mode.md:74 +msgid "" +"Considering there may be a risk of malicious access, please make sure you " +"are under a dev-mode, and explicit specify the develop env: " +"`VLLM_SERVER_DEV_MODE` to expose these endpoints(sleep/wake up)." +msgstr "" +"鉴于可能存在恶意访问的风险，请确保您处于开发模式，并明确指定开发环境：`VLLM_SERVER_DEV_MODE`，以便开放这些端点（sleep/wake" +" up）。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/structured_output.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/structured_output.po new file mode 100644 index 000000000..636e59db7 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/structured_output.po @@ -0,0 +1,220 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/feature_guide/structured_output.md:1 +msgid "Structured Output Guide" +msgstr "结构化输出指南" + +#: ../../user_guide/feature_guide/structured_output.md:3 +msgid "Overview" +msgstr "概述" + +#: ../../user_guide/feature_guide/structured_output.md:5 +msgid "What is Structured Output?" +msgstr "什么是结构化输出？" + +#: ../../user_guide/feature_guide/structured_output.md:7 +msgid "" +"LLMs can be unpredictable when you need output in specific formats. Think of" +" asking a model to generate JSON - without guidance, it might produce valid " +"text that breaks JSON specification. **Structured Output (also called Guided" +" Decoding)** enables LLMs to generate outputs that follow a desired " +"structure while preserving the non-deterministic nature of the system." +msgstr "" +"当你需要特定格式输出时，大型语言模型（LLMs）可能表现出不可预测性。比如让模型生成 " +"JSON，如果没有指导，模型可能会生成有效的文本，但这些文本却不符合 JSON 规范。**结构化输出（也称为引导解码）** " +"能让大型语言模型生成符合预期结构的输出，同时保留系统的非确定性特性。" + +#: ../../user_guide/feature_guide/structured_output.md:9 +msgid "" +"In simple terms, structured decoding gives LLMs a “template” to follow. " +"Users provide a schema that “influences” the model’s output, ensuring " +"compliance with the desired structure." +msgstr "简单来说，结构化解码为LLM提供了一个“模板”来遵循。用户提供一个模式来“影响”模型的输出，从而确保输出符合期望的结构。" + +#: ../../user_guide/feature_guide/structured_output.md:11 +msgid "![structured decoding](./images/structured_output_1.png)" +msgstr "![结构化解码](./images/structured_output_1.png)" + +#: ../../user_guide/feature_guide/structured_output.md:11 +msgid "structured decoding" +msgstr "结构化解码" + +#: ../../user_guide/feature_guide/structured_output.md:13 +msgid "Structured Output in vllm-ascend" +msgstr "vllm-ascend 中的结构化输出" + +#: ../../user_guide/feature_guide/structured_output.md:15 +msgid "" +"Currently, vllm-ascend supports **xgrammar** and **guidance** backend for " +"structured output with vllm v1 engine." +msgstr "目前，vllm-ascend 支持 vllm v1 引擎的结构化输出，后端包括 **xgrammar** 和 **guidance**。" + +#: ../../user_guide/feature_guide/structured_output.md:17 +msgid "" +"XGrammar introduces a new technique that batch constrained decoding via " +"pushdown automaton (PDA). You can think of a PDA as a “collection of FSMs, " +"and each FSM represents a context-free grammar (CFG).” One significant " +"advantage of PDA is its recursive nature, allowing us to execute multiple " +"state transitions. They also include additional optimisation (for those who " +"are interested) to reduce grammar compilation overhead. Besides, you can " +"also find more details about guidance by yourself." +msgstr "" +"XGrammar 引入了一种通过下推自动机（PDA）进行批量约束解码的新技术。你可以把 PDA 理解为“有限状态机（FSM）的集合，每个 FSM " +"代表一个上下文无关文法（CFG）。” PDA 的一个重要优点是其递归特性，使我们能够执行多次状态转移。此外，PDA " +"还包含了额外的优化（供感兴趣的用户参考），以减少语法编译的开销。除此之外，你还可以自己找到更多关于指导的信息。" + +#: ../../user_guide/feature_guide/structured_output.md:19 +msgid "How to Use Structured Output?" +msgstr "如何使用结构化输出？" + +#: ../../user_guide/feature_guide/structured_output.md:21 +msgid "Online Inference" +msgstr "在线推理" + +#: ../../user_guide/feature_guide/structured_output.md:23 +msgid "" +"You can also generate structured outputs using the OpenAI's Completions and " +"Chat API. The following parameters are supported, which must be added as " +"extra parameters:" +msgstr "你也可以使用 OpenAI 的 Completions 和 Chat API 生成结构化输出。支持以下参数，这些参数必须作为额外参数添加：" + +#: ../../user_guide/feature_guide/structured_output.md:25 +msgid "`guided_choice`: the output will be exactly one of the choices." +msgstr "`guided_choice`：输出将会是其中一个选项。" + +#: ../../user_guide/feature_guide/structured_output.md:26 +msgid "`guided_regex`: the output will follow the regex pattern." +msgstr "`guided_regex`：输出将遵循正则表达式模式。" + +#: ../../user_guide/feature_guide/structured_output.md:27 +msgid "`guided_json`: the output will follow the JSON schema." +msgstr "`guided_json`：输出将遵循 JSON 架构。" + +#: ../../user_guide/feature_guide/structured_output.md:28 +msgid "`guided_grammar`: the output will follow the context free grammar." +msgstr "`guided_grammar`：输出将遵循上下文无关文法。" + +#: ../../user_guide/feature_guide/structured_output.md:30 +msgid "" +"Structured outputs are supported by default in the OpenAI-Compatible Server." +" You can choose to specify the backend to use by setting the `--guided-" +"decoding-backend` flag to vllm serve. The default backend is `auto`, which " +"will try to choose an appropriate backend based on the details of the " +"request. You may also choose a specific backend, along with some options." +msgstr "" +"OpenAI 兼容服务器默认支持结构化输出。你可以通过设置 `--guided-decoding-backend` 标志为 vllm serve " +"来指定要使用的后端。默认后端为 `auto`，它会根据请求的详细信息尝试选择合适的后端。你也可以选择特定的后端，并设置一些选项。" + +#: ../../user_guide/feature_guide/structured_output.md:32 +msgid "" +"Now let´s see an example for each of the cases, starting with the " +"guided_choice, as it´s the easiest one:" +msgstr "现在让我们来看每种情况的示例，首先是 guided_choice，因为它是最简单的：" + +#: ../../user_guide/feature_guide/structured_output.md:51 +msgid "" +"The next example shows how to use the guided_regex. The idea is to generate " +"an email address, given a simple regex template:" +msgstr "下一个例子展示了如何使用 guided_regex。其思路是基于一个简单的正则表达式模板生成一个电子邮件地址：" + +#: ../../user_guide/feature_guide/structured_output.md:67 +msgid "" +"One of the most relevant features in structured text generation is the " +"option to generate a valid JSON with pre-defined fields and formats. For " +"this we can use the guided_json parameter in two different ways:" +msgstr "" +"在结构化文本生成中，最相关的特性之一是能够生成具有预定义字段和格式的有效 JSON。为此，我们可以通过两种不同的方式使用 guided_json 参数：" + +#: ../../user_guide/feature_guide/structured_output.md:69 +msgid "Using a JSON Schema." +msgstr "使用 JSON 架构。" + +#: ../../user_guide/feature_guide/structured_output.md:70 +msgid "Defining a Pydantic model and then extracting the JSON Schema from it." +msgstr "定义一个 Pydantic 模型，然后从中提取 JSON Schema。" + +#: ../../user_guide/feature_guide/structured_output.md:72 +msgid "" +"The next example shows how to use the guided_json parameter with a Pydantic " +"model:" +msgstr "下一个示例展示了如何将 guided_json 参数与 Pydantic 模型一起使用：" + +#: ../../user_guide/feature_guide/structured_output.md:104 +msgid "" +"Finally we have the guided_grammar option, which is probably the most " +"difficult to use, but it´s really powerful. It allows us to define complete " +"languages like SQL queries. It works by using a context free EBNF grammar. " +"As an example, we can use to define a specific format of simplified SQL " +"queries:" +msgstr "" +"最后，我们有 guided_grammar 选项，这可能是最难使用的，但它非常强大。它允许我们定义完整的语言，比如 SQL 查询。它通过使用上下文无关的" +" EBNF 语法来实现。例如，我们可以用它来定义一种简化 SQL 查询的特定格式：" + +#: ../../user_guide/feature_guide/structured_output.md:134 +msgid "" +"Find more examples [here](https://github.com/vllm-" +"project/vllm/blob/main/examples/offline_inference/structured_outputs.py)." +msgstr "" +"在[这里](https://github.com/vllm-" +"project/vllm/blob/main/examples/offline_inference/structured_outputs.py)可以找到更多示例。" + +#: ../../user_guide/feature_guide/structured_output.md:136 +msgid "Offline Inference" +msgstr "离线推理" + +#: ../../user_guide/feature_guide/structured_output.md:138 +msgid "" +"To use Structured Output, we'll need to configure the guided decoding using " +"the class `GuidedDecodingParams` inside `SamplingParams`. The main available" +" options inside `GuidedDecodingParams` are:" +msgstr "" +"要使用结构化输出，我们需要在 `SamplingParams` 内通过 `GuidedDecodingParams` " +"类配置引导解码。`GuidedDecodingParams` 中主要可用的选项有：" + +#: ../../user_guide/feature_guide/structured_output.md:140 +msgid "json" +msgstr "json" + +#: ../../user_guide/feature_guide/structured_output.md:141 +msgid "regex" +msgstr "正则表达式" + +#: ../../user_guide/feature_guide/structured_output.md:142 +msgid "choice" +msgstr "选择" + +#: ../../user_guide/feature_guide/structured_output.md:143 +msgid "grammar" +msgstr "语法" + +#: ../../user_guide/feature_guide/structured_output.md:145 +msgid "One example for the usage of the choice parameter is shown below:" +msgstr "choice 参数用法的一个示例如下：" + +#: ../../user_guide/feature_guide/structured_output.md:163 +msgid "" +"Find more examples of other usages [here](https://github.com/vllm-" +"project/vllm/blob/main/examples/offline_inference/structured_outputs.py)." +msgstr "" +"查看更多其他用法的示例 [在这里](https://github.com/vllm-" +"project/vllm/blob/main/examples/offline_inference/structured_outputs.py)。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/release_notes.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/release_notes.po new file mode 100644 index 000000000..ddd1eb542 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/release_notes.po @@ -0,0 +1,1660 @@ +# Translations template for PROJECT. +# Copyright (C) 2025 ORGANIZATION +# This file is distributed under the same license as the PROJECT project. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: PROJECT VERSION\n" +"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: 2025-07-18 10:11+0800\n" +"Last-Translator: \n" +"Language-Team: \n" +"Language: zh\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Generated-By: Babel 2.17.0\n" +"X-Generator: Poedit 3.5\n" + +#: ../../user_guide/release_notes.md:1 +msgid "Release note" +msgstr "版本说明" + +#: ../../user_guide/release_notes.md:3 +msgid "v0.9.2rc1 - 2025.07.11" +msgstr "" + +#: ../../user_guide/release_notes.md:5 +msgid "" +"This is the 1st release candidate of v0.9.2 for vLLM Ascend. Please follow " +"the [official doc](https://vllm-ascend.readthedocs.io/en/) to get started. " +"From this release, V1 engine will be enabled by default, there is no need " +"to set `VLLM_USE_V1=1` any more. And this release is the last version to " +"support V0 engine, V0 code will be clean up in the future." +msgstr "" +"这是 vLLM Ascend v0.9.2 的第一个候选发布版本。请参阅[官方文档](https://vllm-" +"ascend.readthedocs.io/en/)开始使用。从本次发布起，V1 引擎将默认启用，不再需" +"要设置 `VLLM_USE_V1=1`。此外，该版本也是最后一个支持 V0 引擎的版本，V0 相关" +"代码将在未来被清理。" + +#: ../../user_guide/release_notes.md:7 ../../user_guide/release_notes.md:34 +#: ../../user_guide/release_notes.md:70 ../../user_guide/release_notes.md:78 +#: ../../user_guide/release_notes.md:116 ../../user_guide/release_notes.md:140 +#: ../../user_guide/release_notes.md:163 ../../user_guide/release_notes.md:186 +#: ../../user_guide/release_notes.md:206 ../../user_guide/release_notes.md:231 +#: ../../user_guide/release_notes.md:253 ../../user_guide/release_notes.md:285 +msgid "Highlights" +msgstr "亮点" + +#: ../../user_guide/release_notes.md:8 +msgid "" +"Pooling model works with V1 engine now. You can take a try with Qwen3 " +"embedding model [#1359](https://github.com/vllm-project/vllm-ascend/" +"pull/1359)." +msgstr "" +"Pooling 模型现在可以与 V1 引擎一起使用。你可以尝试使用 Qwen3 embedding 模型 " +"[#1359](https://github.com/vllm-project/vllm-ascend/pull/1359)。" + +#: ../../user_guide/release_notes.md:9 +msgid "" +"The performance on Atlas 300I series has been improved. [#1591](https://" +"github.com/vllm-project/vllm-ascend/pull/1591)" +msgstr "" +"Atlas 300I 系列的性能已经提升。 [#1591](https://github.com/vllm-project/" +"vllm-ascend/pull/1591)" + +#: ../../user_guide/release_notes.md:10 +msgid "" +"aclgraph mode works with Moe models now. Currently, only Qwen3 Moe is well " +"tested. [#1381](https://github.com/vllm-project/vllm-ascend/pull/1381)" +msgstr "" +"aclgraph 模式现在可以与 Moe 模型一起使用。目前，仅对 Qwen3 Moe 进行了充分测" +"试。[#1381](https://github.com/vllm-project/vllm-ascend/pull/1381)" + +#: ../../user_guide/release_notes.md:12 ../../user_guide/release_notes.md:39 +#: ../../user_guide/release_notes.md:83 ../../user_guide/release_notes.md:146 +#: ../../user_guide/release_notes.md:168 ../../user_guide/release_notes.md:191 +#: ../../user_guide/release_notes.md:212 ../../user_guide/release_notes.md:236 +#: ../../user_guide/release_notes.md:258 ../../user_guide/release_notes.md:291 +msgid "Core" +msgstr "核心" + +#: ../../user_guide/release_notes.md:13 +msgid "" +"Ascend PyTorch adapter (torch_npu) has been upgraded to `2.5.1.post1." +"dev20250619`. Don’t forget to update it in your environment. [#1347]" +"(https://github.com/vllm-project/vllm-ascend/pull/1347)" +msgstr "" +"Ascend PyTorch 适配器（torch_npu）已升级到 `2.5.1.post1.dev20250619`。请不要" +"忘记在您的环境中进行更新。 [#1347](https://github.com/vllm-project/vllm-" +"ascend/pull/1347)" + +#: ../../user_guide/release_notes.md:14 +msgid "" +"The **GatherV3** error has been fixed with **aclgraph** mode. [#1416]" +"(https://github.com/vllm-project/vllm-ascend/pull/1416)" +msgstr "" +"**GatherV3** 错误已通过 **aclgraph** 模式修复。[#1416](https://github.com/" +"vllm-project/vllm-ascend/pull/1416)" + +#: ../../user_guide/release_notes.md:15 +msgid "" +"W8A8 quantization works on Atlas 300I series now. [#1560](https://github." +"com/vllm-project/vllm-ascend/pull/1560)" +msgstr "" +"W8A8 量化现在可以在 Atlas 300I 系列上运行了。[#1560](https://github.com/" +"vllm-project/vllm-ascend/pull/1560)" + +#: ../../user_guide/release_notes.md:16 +msgid "" +"Fix the accuracy problem with deploy models with parallel parameters. " +"[#1678](https://github.com/vllm-project/vllm-ascend/pull/1678)" +msgstr "" +"修复了使用并行参数部署模型时的准确性问题。[#1678](https://github.com/vllm-" +"project/vllm-ascend/pull/1678)" + +#: ../../user_guide/release_notes.md:17 +msgid "" +"The pre-built wheel package now requires lower version of glibc. Users can " +"use it by `pip install vllm-ascend` directly. [#1582](https://github.com/" +"vllm-project/vllm-ascend/pull/1582)" +msgstr "" +"预编译的 wheel 包现在要求更低版本的 glibc。用户可以直接通过 `pip install " +"vllm-ascend` 使用它。[#1582](https://github.com/vllm-project/vllm-ascend/" +"pull/1582)" + +#: ../../user_guide/release_notes.md:19 ../../user_guide/release_notes.md:99 +#: ../../user_guide/release_notes.md:153 ../../user_guide/release_notes.md:177 +#: ../../user_guide/release_notes.md:195 ../../user_guide/release_notes.md:219 +#: ../../user_guide/release_notes.md:242 ../../user_guide/release_notes.md:266 +#: ../../user_guide/release_notes.md:296 +msgid "Other" +msgstr "其它" + +#: ../../user_guide/release_notes.md:20 +msgid "" +"Official doc has been updated for better read experience. For example, more " +"deployment tutorials are added, user/developer docs are updated. More guide " +"will coming soon." +msgstr "" +"官方文档已更新，以提升阅读体验。例如，增加了更多部署教程，用户/开发者文档已" +"更新。更多指南即将推出。" + +#: ../../user_guide/release_notes.md:21 +msgid "" +"Fix accuracy problem for deepseek V3/R1 models with torchair graph in long " +"sequence predictions. [#1331](https://github.com/vllm-project/vllm-ascend/" +"pull/1331)" +msgstr "" +"修复 deepseek V3/R1 模型在使用 torchair 图进行长序列预测时的精度问题。" +"[#1331](https://github.com/vllm-project/vllm-ascend/pull/1331)" + +#: ../../user_guide/release_notes.md:22 +msgid "" +"A new env variable `VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP` has been added. " +"It enables the fused allgather-experts kernel for Deepseek V3/R1 models. " +"The default value is `0`. [#1335](https://github.com/vllm-project/vllm-" +"ascend/pull/1335)" +msgstr "" +"新增了一个环境变量 `VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP`。它用于启用 " +"Deepseek V3/R1 模型的 fused allgather-experts 内核。默认值为 `0`。[#1335]" +"(https://github.com/vllm-project/vllm-ascend/pull/1335)" + +#: ../../user_guide/release_notes.md:23 +msgid "" +"A new env variable `VLLM_ASCEND_ENABLE_TOPK_TOPP_OPTIMIZATION` has been " +"added to improve the performance of topk-topp sampling. The default value " +"is 0, we'll consider to enable it by default in the future[#1732](https://" +"github.com/vllm-project/vllm-ascend/pull/1732)" +msgstr "" +"新增了一个环境变量 `VLLM_ASCEND_ENABLE_TOPK_TOPP_OPTIMIZATION`，用于提升 " +"topk-topp 采样的性能。该变量默认值为 0，未来我们会考虑默认启用此选项[#1732]" +"(https://github.com/vllm-project/vllm-ascend/pull/1732)。" + +#: ../../user_guide/release_notes.md:24 +msgid "" +"A batch of bugs have been fixed for Data Parallelism case [#1273](https://" +"github.com/vllm-project/vllm-ascend/pull/1273) [#1322](https://github.com/" +"vllm-project/vllm-ascend/pull/1322) [#1275](https://github.com/vllm-project/" +"vllm-ascend/pull/1275) [#1478](https://github.com/vllm-project/vllm-ascend/" +"pull/1478)" +msgstr "" +"已修复了一批与数据并行相关的 bug [#1273](https://github.com/vllm-project/" +"vllm-ascend/pull/1273) [#1322](https://github.com/vllm-project/vllm-ascend/" +"pull/1322) [#1275](https://github.com/vllm-project/vllm-ascend/pull/1275) " +"[#1478](https://github.com/vllm-project/vllm-ascend/pull/1478)" + +#: ../../user_guide/release_notes.md:25 +msgid "" +"The DeepSeek performance has been improved. [#1194](https://github.com/vllm-" +"project/vllm-ascend/pull/1194) [#1395](https://github.com/vllm-project/vllm-" +"ascend/pull/1395) [#1380](https://github.com/vllm-project/vllm-ascend/" +"pull/1380)" +msgstr "" +"DeepSeek 的性能已得到提升。[#1194](https://github.com/vllm-project/vllm-" +"ascend/pull/1194) [#1395](https://github.com/vllm-project/vllm-ascend/" +"pull/1395) [#1380](https://github.com/vllm-project/vllm-ascend/pull/1380)" + +#: ../../user_guide/release_notes.md:26 +msgid "" +"Ascend scheduler works with prefix cache now. [#1446](https://github.com/" +"vllm-project/vllm-ascend/pull/1446)" +msgstr "" +"Ascend 调度器现在支持前缀缓存。[#1446](https://github.com/vllm-project/vllm-" +"ascend/pull/1446)" + +#: ../../user_guide/release_notes.md:27 +msgid "" +"DeepSeek now works with prefix cache now. [#1498](https://github.com/vllm-" +"project/vllm-ascend/pull/1498)" +msgstr "" +"DeepSeek 现在支持前缀缓存了。[#1498](https://github.com/vllm-project/vllm-" +"ascend/pull/1498)" + +#: ../../user_guide/release_notes.md:28 +msgid "" +"Support prompt logprobs to recover ceval accuracy in V1 [#1483](https://" +"github.com/vllm-project/vllm-ascend/pull/1483)" +msgstr "" +"支持使用 prompt logprobs 恢复 V1 的 ceval 准确率 [#1483](https://github.com/" +"vllm-project/vllm-ascend/pull/1483)" + +#: ../../user_guide/release_notes.md:30 +msgid "v0.9.1rc1 - 2025.06.22" +msgstr "v0.9.1rc1 - 2025.06.22" + +#: ../../user_guide/release_notes.md:32 +msgid "" +"This is the 1st release candidate of v0.9.1 for vLLM Ascend. Please follow " +"the [official doc](https://vllm-ascend.readthedocs.io/en/) to get started." +msgstr "" +"这是 vLLM Ascend v0.9.1 的第一个候选发布版本。请按照[官方文档](https://vllm-" +"ascend.readthedocs.io/en/)开始使用。" + +#: ../../user_guide/release_notes.md:36 +msgid "" +"Atlas 300I series is experimental supported in this release. [#1333]" +"(https://github.com/vllm-project/vllm-ascend/pull/1333) After careful " +"consideration, this feature **will NOT be included in v0.9.1-dev branch** " +"taking into account the v0.9.1 release quality and the feature rapid " +"iteration to improve performance on Atlas 300I series. We will improve this " +"from 0.9.2rc1 and later." +msgstr "" +"本版本对 Atlas 300I 系列提供了实验性支持。[#1333](https://github.com/vllm-" +"project/vllm-ascend/pull/1333) 经过慎重考虑，鉴于 v0.9.1 版本发布的质量要求" +"以及 Atlas 300I 系列性能优化的快速迭代，该功能**不会被包含在 v0.9.1-dev 分支" +"中**。我们将在 0.9.2rc1 及之后的版本中进一步完善该功能。" + +#: ../../user_guide/release_notes.md:37 +msgid "" +"Support EAGLE-3 for speculative decoding. [#1032](https://github.com/vllm-" +"project/vllm-ascend/pull/1032)" +msgstr "" +"支持 EAGLE-3 进行推测式解码。[#1032](https://github.com/vllm-project/vllm-" +"ascend/pull/1032)" + +#: ../../user_guide/release_notes.md:40 +msgid "" +"Ascend PyTorch adapter (torch_npu) has been upgraded to `2.5.1.post1." +"dev20250528`. Don’t forget to update it in your environment. [#1235]" +"(https://github.com/vllm-project/vllm-ascend/pull/1235)" +msgstr "" +"Ascend PyTorch 适配器（torch_npu）已升级到 `2.5.1.post1.dev20250528`。请不要" +"忘记在您的环境中进行更新。[#1235](https://github.com/vllm-project/vllm-" +"ascend/pull/1235)" + +#: ../../user_guide/release_notes.md:41 +msgid "" +"Support Atlas 300I series container image. You can get it from [quay.io]" +"(https://quay.io/repository/vllm/vllm-ascend)" +msgstr "" +"支持Atlas 300I系列的容器镜像。你可以从[quay.io](https://quay.io/repository/" +"vllm/vllm-ascend)获取。" + +#: ../../user_guide/release_notes.md:42 +msgid "" +"Fix token-wise padding mechanism to make multi-card graph mode work. [#1300]" +"(https://github.com/vllm-project/vllm-ascend/pull/1300)" +msgstr "" +"修复按 token 填充机制以支持多卡图模式。 [#1300](https://github.com/vllm-" +"project/vllm-ascend/pull/1300)" + +#: ../../user_guide/release_notes.md:43 +msgid "" +"Upgrade vllm to 0.9.1 [#1165]https://github.com/vllm-project/vllm-ascend/" +"pull/1165" +msgstr "" +"将 vllm 升级到 0.9.1 [#1165]https://github.com/vllm-project/vllm-ascend/" +"pull/1165" + +#: ../../user_guide/release_notes.md:45 +msgid "Other Improvements" +msgstr "其他改进" + +#: ../../user_guide/release_notes.md:46 +msgid "" +"Initial support Chunked Prefill for MLA. [#1172](https://github.com/vllm-" +"project/vllm-ascend/pull/1172)" +msgstr "" +"为MLA初步支持分块预填充。 [#1172](https://github.com/vllm-project/vllm-" +"ascend/pull/1172)" + +#: ../../user_guide/release_notes.md:47 +msgid "" +"An example of best practices to run DeepSeek with ETP has been added. " +"[#1101](https://github.com/vllm-project/vllm-ascend/pull/1101)" +msgstr "" +"已新增一个使用 ETP 运行 DeepSeek 的最佳实践示例。[#1101](https://github.com/" +"vllm-project/vllm-ascend/pull/1101)" + +#: ../../user_guide/release_notes.md:48 +msgid "" +"Performance improvements for DeepSeek using the TorchAir graph. [#1098]" +"(https://github.com/vllm-project/vllm-ascend/pull/1098), [#1131](https://" +"github.com/vllm-project/vllm-ascend/pull/1131)" +msgstr "" +"通过使用 TorchAir 图对 DeepSeek 进行了性能提升。[#1098](https://github.com/" +"vllm-project/vllm-ascend/pull/1098), [#1131](https://github.com/vllm-" +"project/vllm-ascend/pull/1131)" + +#: ../../user_guide/release_notes.md:49 +msgid "" +"Supports the speculative decoding feature with AscendScheduler. [#943]" +"(https://github.com/vllm-project/vllm-ascend/pull/943)" +msgstr "" +"支持 AscendScheduler 的预测性解码功能。[#943](https://github.com/vllm-" +"project/vllm-ascend/pull/943)" + +#: ../../user_guide/release_notes.md:50 +msgid "" +"Improve `VocabParallelEmbedding` custom op performance. It will be enabled " +"in the next release. [#796](https://github.com/vllm-project/vllm-ascend/" +"pull/796)" +msgstr "" +"提升 `VocabParallelEmbedding` 自定义算子的性能。该优化将在下一个版本中启用。" +"[#796](https://github.com/vllm-project/vllm-ascend/pull/796)" + +#: ../../user_guide/release_notes.md:51 +msgid "" +"Fixed a device discovery and setup bug when running vLLM Ascend on Ray " +"[#884](https://github.com/vllm-project/vllm-ascend/pull/884)" +msgstr "" +"修复了在 Ray 上运行 vLLM Ascend 时的设备发现和设置错误 [#884](https://" +"github.com/vllm-project/vllm-ascend/pull/884)" + +#: ../../user_guide/release_notes.md:52 +msgid "" +"DeepSeek with [MC2](https://www.hiascend.com/document/detail/zh/" +"canncommercial/81RC1/developmentguide/opdevg/ascendcbestP/" +"atlas_ascendc_best_practices_10_0043.html) (Merged Compute and " +"Communication) now works properly. [#1268](https://github.com/vllm-project/" +"vllm-ascend/pull/1268)" +msgstr "" +"DeepSeek 现已可以与 [MC2](https://www.hiascend.com/document/detail/zh/" +"canncommercial/81RC1/developmentguide/opdevg/ascendcbestP/" +"atlas_ascendc_best_practices_10_0043.html)（计算与通信融合）正常工作。" +"[#1268](https://github.com/vllm-project/vllm-ascend/pull/1268)" + +#: ../../user_guide/release_notes.md:53 +msgid "" +"Fixed log2phy NoneType bug with static EPLB feature. [#1186](https://github." +"com/vllm-project/vllm-ascend/pull/1186)" +msgstr "" +"修复了带有静态 EPLB 特性时 log2phy 为 NoneType 的 bug。[#1186](https://" +"github.com/vllm-project/vllm-ascend/pull/1186)" + +#: ../../user_guide/release_notes.md:54 +msgid "" +"Improved performance for DeepSeek with DBO enabled. [#997](https://github." +"com/vllm-project/vllm-ascend/pull/997), [#1135](https://github.com/vllm-" +"project/vllm-ascend/pull/1135)" +msgstr "" +"启用 DBO 后，DeepSeek 的性能得到提升。[#997](https://github.com/vllm-" +"project/vllm-ascend/pull/997)，[#1135](https://github.com/vllm-project/vllm-" +"ascend/pull/1135)" + +#: ../../user_guide/release_notes.md:55 +msgid "" +"Refactoring AscendFusedMoE [#1229](https://github.com/vllm-project/vllm-" +"ascend/pull/1229)" +msgstr "" +"重构 AscendFusedMoE [#1229](https://github.com/vllm-project/vllm-ascend/" +"pull/1229)" + +#: ../../user_guide/release_notes.md:56 +msgid "" +"Add initial user stories page (include LLaMA-Factory/TRL/verl/MindIE Turbo/" +"GPUStack) [#1224](https://github.com/vllm-project/vllm-ascend/pull/1224)" +msgstr "" +"新增初始用户故事页面（包括 LLaMA-Factory/TRL/verl/MindIE Turbo/GPUStack）" +"[#1224](https://github.com/vllm-project/vllm-ascend/pull/1224)" + +#: ../../user_guide/release_notes.md:57 +msgid "" +"Add unit test framework [#1201](https://github.com/vllm-project/vllm-ascend/" +"pull/1201)" +msgstr "" +"添加单元测试框架 [#1201](https://github.com/vllm-project/vllm-ascend/" +"pull/1201)" + +#: ../../user_guide/release_notes.md:59 +msgid "Known Issues" +msgstr "已知问题" + +#: ../../user_guide/release_notes.md:60 +msgid "" +"In some cases, the vLLM process may crash with a **GatherV3** error when " +"**aclgraph** is enabled. We are working on this issue and will fix it in " +"the next release. [#1038](https://github.com/vllm-project/vllm-ascend/" +"issues/1038)" +msgstr "" +"在某些情况下，当启用 **aclgraph** 时，vLLM 进程可能会因 **GatherV3** 错误而" +"崩溃。我们正在解决此问题，并将在下一个版本中修复。[#1038](https://github." +"com/vllm-project/vllm-ascend/issues/1038)" + +#: ../../user_guide/release_notes.md:61 +msgid "" +"Prefix cache feature does not work with the Ascend Scheduler but without " +"chunked prefill enabled. This will be fixed in the next release. [#1350]" +"(https://github.com/vllm-project/vllm-ascend/issues/1350)" +msgstr "" +"前缀缓存功能在未启用分块预填充的情况下无法与 Ascend 调度器一同工作。此问题将" +"在下一个版本中修复。[#1350](https://github.com/vllm-project/vllm-ascend/" +"issues/1350)" + +#: ../../user_guide/release_notes.md:63 +msgid "Full Changelog" +msgstr "完整更新日志" + +#: ../../user_guide/release_notes.md:64 +msgid "" +"https://github.com/vllm-project/vllm-ascend/compare/v0.9.0rc2...v0.9.1rc1" +msgstr "" +"https://github.com/vllm-project/vllm-ascend/compare/v0.9.0rc2...v0.9.1rc1" + +#: ../../user_guide/release_notes.md:66 +msgid "v0.9.0rc2 - 2025.06.10" +msgstr "v0.9.0rc2 - 2025.06.10" + +#: ../../user_guide/release_notes.md:68 +msgid "" +"This release contains some quick fixes for v0.9.0rc1. Please use this " +"release instead of v0.9.0rc1." +msgstr "" +"本次发布包含了一些针对 v0.9.0rc1 的快速修复。请使用本次发布版本，而不是 " +"v0.9.0rc1。" + +#: ../../user_guide/release_notes.md:72 +msgid "" +"Fix the import error when vllm-ascend is installed without editable way. " +"[#1152](https://github.com/vllm-project/vllm-ascend/pull/1152)" +msgstr "" +"修复当以非可编辑方式安装 vllm-ascend 时的导入错误。[#1152](https://github." +"com/vllm-project/vllm-ascend/pull/1152)" + +#: ../../user_guide/release_notes.md:74 +msgid "v0.9.0rc1 - 2025.06.09" +msgstr "v0.9.0rc1 - 2025.06.09" + +#: ../../user_guide/release_notes.md:76 +msgid "" +"This is the 1st release candidate of v0.9.0 for vllm-ascend. Please follow " +"the [official doc](https://vllm-ascend.readthedocs.io/en/) to start the " +"journey. From this release, V1 Engine is recommended to use. The code of V0 " +"Engine is frozen and will not be maintained any more. Please set " +"environment `VLLM_USE_V1=1` to enable V1 Engine." +msgstr "" +"这是 vllm-ascend v0.9.0 的第一个候选发布版本。请按照[官方文档](https://vllm-" +"ascend.readthedocs.io/en/)开始使用。从此版本起，推荐使用 V1 引擎。V0 引擎的" +"代码已被冻结，不再维护。如需启用 V1 引擎，请设置环境变量 `VLLM_USE_V1=1`。" + +#: ../../user_guide/release_notes.md:80 +msgid "" +"DeepSeek works with graph mode now. Follow the [official doc](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/feature_guide/graph_mode.html) " +"to take a try. [#789](https://github.com/vllm-project/vllm-ascend/pull/789)" +msgstr "" +"DeepSeek 现在已支持图模式。请按照[官方文档](https://vllm-ascend.readthedocs." +"io/en/latest/user_guide/feature_guide/graph_mode.html)进行尝试。[#789]" +"(https://github.com/vllm-project/vllm-ascend/pull/789)" + +#: ../../user_guide/release_notes.md:81 +msgid "" +"Qwen series models works with graph mode now. It works by default with V1 " +"Engine. Please note that in this release, only Qwen series models are well " +"tested with graph mode. We'll make it stable and generalize in the next " +"release. If you hit any issues, please feel free to open an issue on GitHub " +"and fallback to eager mode temporarily by set `enforce_eager=True` when " +"initializing the model." +msgstr "" +"Qwen 系列模型现在支持图模式。默认情况下，它在 V1 引擎下运行。请注意，本次发" +"布中，仅 Qwen 系列模型经过了充分的图模式测试。我们将在下一个版本中进一步提升" +"其稳定性并推广至更广泛的场景。如果你遇到任何问题，请随时在 GitHub 上提交 " +"issue，并在初始化模型时通过设置 `enforce_eager=True` 临时切换回 eager 模式。" + +#: ../../user_guide/release_notes.md:85 +msgid "" +"The performance of multi-step scheduler has been improved. Thanks for the " +"contribution from China Merchants Bank. [#814](https://github.com/vllm-" +"project/vllm-ascend/pull/814)" +msgstr "" +"多步调度器的性能得到了提升。感谢招商银行的贡献。[#814](https://github.com/" +"vllm-project/vllm-ascend/pull/814)" + +#: ../../user_guide/release_notes.md:86 +msgid "" +"LoRA、Multi-LoRA And Dynamic Serving is supported for V1 Engine now. Thanks " +"for the contribution from China Merchants Bank. [#893](https://github.com/" +"vllm-project/vllm-ascend/pull/893)" +msgstr "" +"V1 引擎现在支持 LoRA、多 LoRA 以及动态服务。感谢招商银行的贡献。[#893]" +"(https://github.com/vllm-project/vllm-ascend/pull/893)" + +#: ../../user_guide/release_notes.md:87 +msgid "" +"Prefix cache and chunked prefill feature works now [#782](https://github." +"com/vllm-project/vllm-ascend/pull/782) [#844](https://github.com/vllm-" +"project/vllm-ascend/pull/844)" +msgstr "" +"前缀缓存和分块预填充功能现已可用 [#782](https://github.com/vllm-project/" +"vllm-ascend/pull/782) [#844](https://github.com/vllm-project/vllm-ascend/" +"pull/844)" + +#: ../../user_guide/release_notes.md:88 +msgid "" +"Spec decode and MTP features work with V1 Engine now. [#874](https://github." +"com/vllm-project/vllm-ascend/pull/874) [#890](https://github.com/vllm-" +"project/vllm-ascend/pull/890)" +msgstr "" +"Spec 解码和 MTP 功能现在已经支持 V1 引擎。[#874](https://github.com/vllm-" +"project/vllm-ascend/pull/874) [#890](https://github.com/vllm-project/vllm-" +"ascend/pull/890)" + +#: ../../user_guide/release_notes.md:89 +msgid "" +"DP feature works with DeepSeek now. [#1012](https://github.com/vllm-project/" +"vllm-ascend/pull/1012)" +msgstr "" +"DP 功能现在可以与 DeepSeek 一起使用。[#1012](https://github.com/vllm-" +"project/vllm-ascend/pull/1012)" + +#: ../../user_guide/release_notes.md:90 +msgid "" +"Input embedding feature works with V0 Engine now. [#916](https://github.com/" +"vllm-project/vllm-ascend/pull/916)" +msgstr "" +"输入嵌入特性现在已支持 V0 引擎。[#916](https://github.com/vllm-project/vllm-" +"ascend/pull/916)" + +#: ../../user_guide/release_notes.md:91 +msgid "" +"Sleep mode feature works with V1 Engine now. [#1084](https://github.com/" +"vllm-project/vllm-ascend/pull/1084)" +msgstr "" +"休眠模式功能现在已支持 V1 引擎。[#1084](https://github.com/vllm-project/" +"vllm-ascend/pull/1084)" + +#: ../../user_guide/release_notes.md:93 ../../user_guide/release_notes.md:149 +#: ../../user_guide/release_notes.md:239 ../../user_guide/release_notes.md:262 +msgid "Model" +msgstr "模型" + +#: ../../user_guide/release_notes.md:95 +msgid "" +"Qwen2.5 VL works with V1 Engine now. [#736](https://github.com/vllm-project/" +"vllm-ascend/pull/736)" +msgstr "" +"Qwen2.5 VL 现在可以与 V1 引擎协同工作。[#736](https://github.com/vllm-" +"project/vllm-ascend/pull/736)" + +#: ../../user_guide/release_notes.md:96 +msgid "" +"LLama4 works now. [#740](https://github.com/vllm-project/vllm-ascend/" +"pull/740)" +msgstr "" +"LLama4 现在可以使用了。[#740](https://github.com/vllm-project/vllm-ascend/" +"pull/740)" + +#: ../../user_guide/release_notes.md:97 +msgid "" +"A new kind of DeepSeek model called dual-batch overlap(DBO) is added. " +"Please set `VLLM_ASCEND_ENABLE_DBO=1` to use it. [#941](https://github.com/" +"vllm-project/vllm-ascend/pull/941)" +msgstr "" +"新增了一种名为双批次重叠（dual-batch overlap，DBO）的 DeepSeek 模型。请设置 " +"`VLLM_ASCEND_ENABLE_DBO=1` 以启用。 [#941](https://github.com/vllm-project/" +"vllm-ascend/pull/941)" + +#: ../../user_guide/release_notes.md:101 +msgid "" +"online serve with ascend quantization works now. [#877](https://github.com/" +"vllm-project/vllm-ascend/pull/877)" +msgstr "" +"在线服务现已支持Ascend量化。[#877](https://github.com/vllm-project/vllm-" +"ascend/pull/877)" + +#: ../../user_guide/release_notes.md:102 +msgid "" +"A batch of bugs for graph mode and moe model have been fixed. [#773]" +"(https://github.com/vllm-project/vllm-ascend/pull/773) [#771](https://" +"github.com/vllm-project/vllm-ascend/pull/771) [#774](https://github.com/" +"vllm-project/vllm-ascend/pull/774) [#816](https://github.com/vllm-project/" +"vllm-ascend/pull/816) [#817](https://github.com/vllm-project/vllm-ascend/" +"pull/817) [#819](https://github.com/vllm-project/vllm-ascend/pull/819) " +"[#912](https://github.com/vllm-project/vllm-ascend/pull/912) [#897](https://" +"github.com/vllm-project/vllm-ascend/pull/897) [#961](https://github.com/" +"vllm-project/vllm-ascend/pull/961) [#958](https://github.com/vllm-project/" +"vllm-ascend/pull/958) [#913](https://github.com/vllm-project/vllm-ascend/" +"pull/913) [#905](https://github.com/vllm-project/vllm-ascend/pull/905)" +msgstr "" +"已修复一批关于图模式和moe模型的bug。[#773](https://github.com/vllm-project/" +"vllm-ascend/pull/773) [#771](https://github.com/vllm-project/vllm-ascend/" +"pull/771) [#774](https://github.com/vllm-project/vllm-ascend/pull/774) " +"[#816](https://github.com/vllm-project/vllm-ascend/pull/816) [#817](https://" +"github.com/vllm-project/vllm-ascend/pull/817) [#819](https://github.com/" +"vllm-project/vllm-ascend/pull/819) [#912](https://github.com/vllm-project/" +"vllm-ascend/pull/912) [#897](https://github.com/vllm-project/vllm-ascend/" +"pull/897) [#961](https://github.com/vllm-project/vllm-ascend/pull/961) " +"[#958](https://github.com/vllm-project/vllm-ascend/pull/958) [#913](https://" +"github.com/vllm-project/vllm-ascend/pull/913) [#905](https://github.com/" +"vllm-project/vllm-ascend/pull/905)" + +#: ../../user_guide/release_notes.md:103 +msgid "" +"A batch of performance improvement PRs have been merged. [#784](https://" +"github.com/vllm-project/vllm-ascend/pull/784) [#803](https://github.com/" +"vllm-project/vllm-ascend/pull/803) [#966](https://github.com/vllm-project/" +"vllm-ascend/pull/966) [#839](https://github.com/vllm-project/vllm-ascend/" +"pull/839) [#970](https://github.com/vllm-project/vllm-ascend/pull/970) " +"[#947](https://github.com/vllm-project/vllm-ascend/pull/947) [#987](https://" +"github.com/vllm-project/vllm-ascend/pull/987) [#1085](https://github.com/" +"vllm-project/vllm-ascend/pull/1085)" +msgstr "" +"一批性能改进的 PR 已被合并。[#784](https://github.com/vllm-project/vllm-" +"ascend/pull/784) [#803](https://github.com/vllm-project/vllm-ascend/" +"pull/803) [#966](https://github.com/vllm-project/vllm-ascend/pull/966) " +"[#839](https://github.com/vllm-project/vllm-ascend/pull/839) [#970](https://" +"github.com/vllm-project/vllm-ascend/pull/970) [#947](https://github.com/" +"vllm-project/vllm-ascend/pull/947) [#987](https://github.com/vllm-project/" +"vllm-ascend/pull/987) [#1085](https://github.com/vllm-project/vllm-ascend/" +"pull/1085)" + +#: ../../user_guide/release_notes.md:104 +msgid "" +"From this release, binary wheel package will be released as well. [#775]" +"(https://github.com/vllm-project/vllm-ascend/pull/775)" +msgstr "" +"从本版本开始，将同时发布二进制 wheel 包。[#775](https://github.com/vllm-" +"project/vllm-ascend/pull/775)" + +#: ../../user_guide/release_notes.md:105 +msgid "" +"The contributor doc site is [added](https://vllm-ascend.readthedocs.io/en/" +"latest/community/contributors.html)" +msgstr "" +"贡献者文档站点已[添加](https://vllm-ascend.readthedocs.io/en/latest/" +"community/contributors.html)" + +#: ../../user_guide/release_notes.md:107 +msgid "Known Issue" +msgstr "已知问题" + +#: ../../user_guide/release_notes.md:109 +msgid "" +"In some case, vLLM process may be crashed with aclgraph enabled. We're " +"working this issue and it'll be fixed in the next release." +msgstr "" +"在某些情况下，启用 aclgraph 时 vLLM 进程可能会崩溃。我们正在处理这个问题，并" +"将在下一个版本中修复。" + +#: ../../user_guide/release_notes.md:110 +msgid "" +"Multi node data-parallel doesn't work with this release. This is a known " +"issue in vllm and has been fixed on main branch. [#18981](https://github." +"com/vllm-project/vllm/pull/18981)" +msgstr "" +"多节点数据并行在此版本中无法使用。这是 vllm 中已知的问题，并已在主分支中修" +"复。 [#18981](https://github.com/vllm-project/vllm/pull/18981)" + +#: ../../user_guide/release_notes.md:112 +msgid "v0.7.3.post1 - 2025.05.29" +msgstr "v0.7.3.post1 - 2025.05.29" + +#: ../../user_guide/release_notes.md:114 +msgid "" +"This is the first post release of 0.7.3. Please follow the [official doc]" +"(https://vllm-ascend.readthedocs.io/en/v0.7.3-dev) to start the journey. It " +"includes the following changes:" +msgstr "" +"这是 0.7.3 的第一个补丁发布。请按照[官方文档](https://vllm-ascend." +"readthedocs.io/en/v0.7.3-dev)开始使用。本次更新包括以下更改：" + +#: ../../user_guide/release_notes.md:118 +msgid "" +"Qwen3 and Qwen3MOE is supported now. The performance and accuracy of Qwen3 " +"is well tested. You can try it now. Mindie Turbo is recomanded to improve " +"the performance of Qwen3. [#903](https://github.com/vllm-project/vllm-" +"ascend/pull/903) [#915](https://github.com/vllm-project/vllm-ascend/" +"pull/915)" +msgstr "" +"现在已支持 Qwen3 和 Qwen3MOE。Qwen3 的性能和精度已经过充分测试，你可以立即试" +"用。推荐使用 Mindie Turbo 以提升 Qwen3 的性能。[#903](https://github.com/" +"vllm-project/vllm-ascend/pull/903) [#915](https://github.com/vllm-project/" +"vllm-ascend/pull/915)" + +#: ../../user_guide/release_notes.md:119 +msgid "" +"Added a new performance guide. The guide aims to help users to improve vllm-" +"ascend performance on system level. It includes OS configuration, library " +"optimization, deploy guide and so on. [#878](https://github.com/vllm-" +"project/vllm-ascend/pull/878) [Doc Link](https://vllm-ascend.readthedocs.io/" +"en/v0.7.3-dev/developer_guide/performance/optimization_and_tuning.html)" +msgstr "" +"新增了一个性能指南。该指南旨在帮助用户在系统层面提升 vllm-ascend 的性能。内" +"容包括操作系统配置、库优化、部署指南等。 [#878](https://github.com/vllm-" +"project/vllm-ascend/pull/878) [文档链接](https://vllm-ascend.readthedocs.io/" +"en/v0.7.3-dev/developer_guide/performance/optimization_and_tuning.html)" + +#: ../../user_guide/release_notes.md:121 +msgid "Bug Fix" +msgstr "漏洞修复" + +#: ../../user_guide/release_notes.md:123 +msgid "" +"Qwen2.5-VL works for RLHF scenarios now. [#928](https://github.com/vllm-" +"project/vllm-ascend/pull/928)" +msgstr "" +"Qwen2.5-VL 现在已支持 RLHF 场景。[#928](https://github.com/vllm-project/" +"vllm-ascend/pull/928)" + +#: ../../user_guide/release_notes.md:124 +msgid "" +"Users can launch the model from online weights now. e.g. from huggingface " +"or modelscope directly [#858](https://github.com/vllm-project/vllm-ascend/" +"pull/858) [#918](https://github.com/vllm-project/vllm-ascend/pull/918)" +msgstr "" +"用户现在可以直接从在线权重启动模型。例如，可以直接从 huggingface 或 " +"modelscope 获取。[#858](https://github.com/vllm-project/vllm-ascend/" +"pull/858) [#918](https://github.com/vllm-project/vllm-ascend/pull/918)" + +#: ../../user_guide/release_notes.md:125 +msgid "" +"The meaningless log info `UserWorkspaceSize0` has been cleaned. [#911]" +"(https://github.com/vllm-project/vllm-ascend/pull/911)" +msgstr "" +"无意义的日志信息 `UserWorkspaceSize0` 已被清理。[#911](https://github.com/" +"vllm-project/vllm-ascend/pull/911)" + +#: ../../user_guide/release_notes.md:126 +msgid "" +"The log level for `Failed to import vllm_ascend_C` has been changed to " +"`warning` instead of `error`. [#956](https://github.com/vllm-project/vllm-" +"ascend/pull/956)" +msgstr "" +"`Failed to import vllm_ascend_C` 的日志级别已从 `error` 更改为 `warning`。" +"[#956](https://github.com/vllm-project/vllm-ascend/pull/956)" + +#: ../../user_guide/release_notes.md:127 +msgid "" +"DeepSeek MLA now works with chunked prefill in V1 Engine. Please note that " +"V1 engine in 0.7.3 is just expermential and only for test usage. [#849]" +"(https://github.com/vllm-project/vllm-ascend/pull/849) [#936](https://" +"github.com/vllm-project/vllm-ascend/pull/936)" +msgstr "" +"DeepSeek MLA 现已在 V1 引擎中支持分块预填充。请注意，0.7.3 版本中的 V1 引擎" +"仅为实验性，仅供测试使用。[#849](https://github.com/vllm-project/vllm-" +"ascend/pull/849) [#936](https://github.com/vllm-project/vllm-ascend/" +"pull/936)" + +#: ../../user_guide/release_notes.md:129 +msgid "Docs" +msgstr "文档" + +#: ../../user_guide/release_notes.md:131 +msgid "" +"The benchmark doc is updated for Qwen2.5 and Qwen2.5-VL [#792](https://" +"github.com/vllm-project/vllm-ascend/pull/792)" +msgstr "" +"基准文档已针对 Qwen2.5 和 Qwen2.5-VL 更新 [#792](https://github.com/vllm-" +"project/vllm-ascend/pull/792)" + +#: ../../user_guide/release_notes.md:132 +msgid "" +"Add the note to clear that only \"modelscope<1.23.0\" works with 0.7.3. " +"[#954](https://github.com/vllm-project/vllm-ascend/pull/954)" +msgstr "" +"添加说明，明确只有 \"modelscope<1.23.0\" 能与 0.7.3 一起使用。[#954]" +"(https://github.com/vllm-project/vllm-ascend/pull/954)" + +#: ../../user_guide/release_notes.md:134 +msgid "v0.7.3 - 2025.05.08" +msgstr "v0.7.3 - 2025.05.08" + +#: ../../user_guide/release_notes.md:136 ../../user_guide/release_notes.md:277 +msgid "🎉 Hello, World!" +msgstr "🎉 你好，世界！" + +#: ../../user_guide/release_notes.md:138 +msgid "" +"We are excited to announce the release of 0.7.3 for vllm-ascend. This is " +"the first official release. The functionality, performance, and stability " +"of this release are fully tested and verified. We encourage you to try it " +"out and provide feedback. We'll post bug fix versions in the future if " +"needed. Please follow the [official doc](https://vllm-ascend.readthedocs.io/" +"en/v0.7.3-dev) to start the journey." +msgstr "" +"我们很高兴地宣布 vllm-ascend 0.7.3 版本正式发布。这是首个正式发布的版本。该" +"版本的功能、性能和稳定性已充分测试和验证。我们鼓励您试用并反馈意见。如有需" +"要，未来我们将发布修复版本。请参阅[官方文档](https://vllm-ascend." +"readthedocs.io/en/v0.7.3-dev)开启您的体验之旅。" + +#: ../../user_guide/release_notes.md:141 +msgid "" +"This release includes all features landed in the previous release " +"candidates ([v0.7.1rc1](https://github.com/vllm-project/vllm-ascend/" +"releases/tag/v0.7.1rc1), [v0.7.3rc1](https://github.com/vllm-project/vllm-" +"ascend/releases/tag/v0.7.3rc1), [v0.7.3rc2](https://github.com/vllm-project/" +"vllm-ascend/releases/tag/v0.7.3rc2)). And all the features are fully tested " +"and verified. Visit the official doc the get the detail [feature](https://" +"vllm-ascend.readthedocs.io/en/v0.7.3-dev/user_guide/suppoted_features.html) " +"and [model](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/user_guide/" +"supported_models.html) support matrix." +msgstr "" +"本次发布包含了所有在之前候选版本中加入的功能（[v0.7.1rc1](https://github." +"com/vllm-project/vllm-ascend/releases/tag/v0.7.1rc1)、[v0.7.3rc1](https://" +"github.com/vllm-project/vllm-ascend/releases/tag/v0.7.3rc1)、[v0.7.3rc2]" +"(https://github.com/vllm-project/vllm-ascend/releases/tag/v0.7.3rc2)）。所有" +"功能都经过了全面测试和验证。请访问官方文档获取详细的[功能](https://vllm-" +"ascend.readthedocs.io/en/v0.7.3-dev/user_guide/suppoted_features.html)和[模" +"型](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/user_guide/" +"supported_models.html)支持矩阵。" + +#: ../../user_guide/release_notes.md:142 +msgid "" +"Upgrade CANN to 8.1.RC1 to enable chunked prefill and automatic prefix " +"caching features. You can now enable them now." +msgstr "" +"将 CANN 升级到 8.1.RC1 以启用分块预填充和自动前缀缓存功能。您现在可以启用这" +"些功能了。" + +#: ../../user_guide/release_notes.md:143 +msgid "" +"Upgrade PyTorch to 2.5.1. vLLM Ascend no longer relies on the dev version " +"of torch-npu now. Now users don't need to install the torch-npu by hand. " +"The 2.5.1 version of torch-npu will be installed automatically. [#662]" +"(https://github.com/vllm-project/vllm-ascend/pull/662)" +msgstr "" +"升级 PyTorch 至 2.5.1。vLLM Ascend 现在不再依赖于 torch-npu 的开发版本。用户" +"现在无需手动安装 torch-npu，2.5.1 版本的 torch-npu 会被自动安装。[#662]" +"(https://github.com/vllm-project/vllm-ascend/pull/662)" + +#: ../../user_guide/release_notes.md:144 +msgid "" +"Integrate MindIE Turbo into vLLM Ascend to improve DeepSeek V3/R1, Qwen 2 " +"series performance. [#708](https://github.com/vllm-project/vllm-ascend/" +"pull/708)" +msgstr "" +"将 MindIE Turbo 集成到 vLLM Ascend 以提升 DeepSeek V3/R1、Qwen 2 系列的性" +"能。[#708](https://github.com/vllm-project/vllm-ascend/pull/708)" + +#: ../../user_guide/release_notes.md:147 +msgid "" +"LoRA、Multi-LoRA And Dynamic Serving is supported now. The performance will " +"be improved in the next release. Please follow the official doc for more " +"usage information. Thanks for the contribution from China Merchants Bank. " +"[#700](https://github.com/vllm-project/vllm-ascend/pull/700)" +msgstr "" +"现在已经支持 LoRA、多LoRA 和动态服务。下一个版本中性能将会提升。请参阅官方文" +"档以获取更多用法信息。感谢招商银行的贡献。[#700](https://github.com/vllm-" +"project/vllm-ascend/pull/700)" + +#: ../../user_guide/release_notes.md:150 +msgid "" +"The performance of Qwen2 vl and Qwen2.5 vl is improved. [#702](https://" +"github.com/vllm-project/vllm-ascend/pull/702)" +msgstr "" +"Qwen2 vl 和 Qwen2.5 vl 的性能得到了提升。 [#702](https://github.com/vllm-" +"project/vllm-ascend/pull/702)" + +#: ../../user_guide/release_notes.md:151 +msgid "" +"The performance of `apply_penalties` and `topKtopP` ops are improved. [#525]" +"(https://github.com/vllm-project/vllm-ascend/pull/525)" +msgstr "" +"`apply_penalties` 和 `topKtopP` 操作的性能得到了提升。 [#525](https://" +"github.com/vllm-project/vllm-ascend/pull/525)" + +#: ../../user_guide/release_notes.md:154 +msgid "" +"Fixed a issue that may lead CPU memory leak. [#691](https://github.com/vllm-" +"project/vllm-ascend/pull/691) [#712](https://github.com/vllm-project/vllm-" +"ascend/pull/712)" +msgstr "" +"修复了可能导致CPU内存泄漏的问题。 [#691](https://github.com/vllm-project/" +"vllm-ascend/pull/691) [#712](https://github.com/vllm-project/vllm-ascend/" +"pull/712)" + +#: ../../user_guide/release_notes.md:155 +msgid "" +"A new environment `SOC_VERSION` is added. If you hit any soc detection " +"error when building with custom ops enabled, please set `SOC_VERSION` to a " +"suitable value. [#606](https://github.com/vllm-project/vllm-ascend/pull/606)" +msgstr "" +"新增了一个环境变量 `SOC_VERSION`。如果在启用自定义算子时构建过程中遇到 soc " +"检测错误，请将 `SOC_VERSION` 设置为合适的值。[#606](https://github.com/vllm-" +"project/vllm-ascend/pull/606)" + +#: ../../user_guide/release_notes.md:156 +msgid "" +"openEuler container image supported with v0.7.3-openeuler tag. [#665]" +"(https://github.com/vllm-project/vllm-ascend/pull/665)" +msgstr "" +"openEuler 容器镜像已支持 v0.7.3-openeuler 标签。[#665](https://github.com/" +"vllm-project/vllm-ascend/pull/665)" + +#: ../../user_guide/release_notes.md:157 +msgid "" +"Prefix cache feature works on V1 engine now. [#559](https://github.com/vllm-" +"project/vllm-ascend/pull/559)" +msgstr "" +"前缀缓存功能现在已在 V1 引擎上工作。[#559](https://github.com/vllm-project/" +"vllm-ascend/pull/559)" + +#: ../../user_guide/release_notes.md:159 +msgid "v0.8.5rc1 - 2025.05.06" +msgstr "v0.8.5rc1 - 2025.05.06" + +#: ../../user_guide/release_notes.md:161 +msgid "" +"This is the 1st release candidate of v0.8.5 for vllm-ascend. Please follow " +"the [official doc](https://vllm-ascend.readthedocs.io/en/) to start the " +"journey. Now you can enable V1 egnine by setting the environment variable " +"`VLLM_USE_V1=1`, see the feature support status of vLLM Ascend in [here]" +"(https://vllm-ascend.readthedocs.io/en/latest/user_guide/support_matrix/" +"supported_features.html)." +msgstr "" +"这是 vllm-ascend v0.8.5 的第一个候选发布版本。请按照[官方文档](https://vllm-" +"ascend.readthedocs.io/en/)开始使用。现在，您可以通过设置环境变量 " +"`VLLM_USE_V1=1` 启用 V1 引擎。关于 vLLM Ascend 的特性支持情况，请参见[这里]" +"(https://vllm-ascend.readthedocs.io/en/latest/user_guide/support_matrix/" +"supported_features.html)。" + +#: ../../user_guide/release_notes.md:164 +msgid "" +"Upgrade CANN version to 8.1.RC1 to support chunked prefill and automatic " +"prefix caching (`--enable_prefix_caching`) when V1 is enabled [#747]" +"(https://github.com/vllm-project/vllm-ascend/pull/747)" +msgstr "" +"将 CANN 版本升级到 8.1.RC1，以支持在启用 V1 时的分块预填充和自动前缀缓存" +"（`--enable_prefix_caching`）[#747](https://github.com/vllm-project/vllm-" +"ascend/pull/747)" + +#: ../../user_guide/release_notes.md:165 +msgid "" +"Optimize Qwen2 VL and Qwen 2.5 VL [#701](https://github.com/vllm-project/" +"vllm-ascend/pull/701)" +msgstr "" +"优化 Qwen2 VL 和 Qwen 2.5 VL [#701](https://github.com/vllm-project/vllm-" +"ascend/pull/701)" + +#: ../../user_guide/release_notes.md:166 +#, python-brace-format +msgid "" +"Improve Deepseek V3 eager mode and graph mode performance, now you can use " +"--additional_config={'enable_graph_mode': True} to enable graph mode. [#598]" +"(https://github.com/vllm-project/vllm-ascend/pull/598) [#719](https://" +"github.com/vllm-project/vllm-ascend/pull/719)" +msgstr "" +"改进了 Deepseek V3 的 eager 模式和图模式性能，现在你可以使用 --" +"additional_config={'enable_graph_mode': True} 来启用图模式。[#598](https://" +"github.com/vllm-project/vllm-ascend/pull/598) [#719](https://github.com/" +"vllm-project/vllm-ascend/pull/719)" + +#: ../../user_guide/release_notes.md:169 +msgid "" +"Upgrade vLLM to 0.8.5.post1 [#715](https://github.com/vllm-project/vllm-" +"ascend/pull/715)" +msgstr "" +"将 vLLM 升级到 0.8.5.post1 [#715](https://github.com/vllm-project/vllm-" +"ascend/pull/715)" + +#: ../../user_guide/release_notes.md:170 +msgid "" +"Fix early return in CustomDeepseekV2MoE.forward during profile_run [#682]" +"(https://github.com/vllm-project/vllm-ascend/pull/682)" +msgstr "" +"修复在 profile_run 期间 CustomDeepseekV2MoE.forward 过早返回的问题 [#682]" +"(https://github.com/vllm-project/vllm-ascend/pull/682)" + +#: ../../user_guide/release_notes.md:171 +msgid "" +"Adapts for new quant model generated by modelslim [#719](https://github.com/" +"vllm-project/vllm-ascend/pull/719)" +msgstr "" +"适配由 modelslim 生成的新量化模型 [#719](https://github.com/vllm-project/" +"vllm-ascend/pull/719)" + +#: ../../user_guide/release_notes.md:172 +msgid "" +"Initial support on P2P Disaggregated Prefill based on llm_datadist [#694]" +"(https://github.com/vllm-project/vllm-ascend/pull/694)" +msgstr "" +"基于 llm_datadist 的 P2P 分布式 Prefill 初步支持 [#694](https://github.com/" +"vllm-project/vllm-ascend/pull/694)" + +#: ../../user_guide/release_notes.md:173 +msgid "" +"Use `/vllm-workspace` as code path and include `.git` in container image to " +"fix issue when start vllm under `/workspace` [#726](https://github.com/vllm-" +"project/vllm-ascend/pull/726)" +msgstr "" +"使用 `/vllm-workspace` 作为代码路径，并在容器镜像中包含 `.git` ，以修复在 `/" +"workspace` 下启动 vllm 时的问题 [#726](https://github.com/vllm-project/vllm-" +"ascend/pull/726)" + +#: ../../user_guide/release_notes.md:174 +msgid "" +"Optimize NPU memory usage to make DeepSeek R1 W8A8 32K model len work. " +"[#728](https://github.com/vllm-project/vllm-ascend/pull/728)" +msgstr "" +"优化NPU内存使用，以使 DeepSeek R1 W8A8 32K 模型长度能够运行。[#728](https://" +"github.com/vllm-project/vllm-ascend/pull/728)" + +#: ../../user_guide/release_notes.md:175 +msgid "" +"Fix `PYTHON_INCLUDE_PATH` typo in setup.py [#762](https://github.com/vllm-" +"project/vllm-ascend/pull/762)" +msgstr "" +"修复 setup.py 中的 `PYTHON_INCLUDE_PATH` 拼写错误 [#762](https://github.com/" +"vllm-project/vllm-ascend/pull/762)" + +#: ../../user_guide/release_notes.md:178 +msgid "" +"Add Qwen3-0.6B test [#717](https://github.com/vllm-project/vllm-ascend/" +"pull/717)" +msgstr "" +"添加 Qwen3-0.6B 测试 [#717](https://github.com/vllm-project/vllm-ascend/" +"pull/717)" + +#: ../../user_guide/release_notes.md:179 +msgid "" +"Add nightly CI [#668](https://github.com/vllm-project/vllm-ascend/pull/668)" +msgstr "" +"添加每晚持续集成 [#668](https://github.com/vllm-project/vllm-ascend/" +"pull/668)" + +#: ../../user_guide/release_notes.md:180 +msgid "" +"Add accuracy test report [#542](https://github.com/vllm-project/vllm-ascend/" +"pull/542)" +msgstr "" +"添加准确性测试报告 [#542](https://github.com/vllm-project/vllm-ascend/" +"pull/542)" + +#: ../../user_guide/release_notes.md:182 +msgid "v0.8.4rc2 - 2025.04.29" +msgstr "v0.8.4rc2 - 2025.04.29" + +#: ../../user_guide/release_notes.md:184 +msgid "" +"This is the second release candidate of v0.8.4 for vllm-ascend. Please " +"follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to start " +"the journey. Some experimental features are included in this version, such " +"as W8A8 quantization and EP/DP support. We'll make them stable enough in " +"the next release." +msgstr "" +"这是 vllm-ascend 的 v0.8.4 第二个候选版本。请按照[官方文档](https://vllm-" +"ascend.readthedocs.io/en/)开始使用。本版本包含了一些实验性功能，如 W8A8 量化" +"和 EP/DP 支持。我们将在下一个版本中使这些功能更加稳定。" + +#: ../../user_guide/release_notes.md:187 +msgid "" +"Qwen3 and Qwen3MOE is supported now. Please follow the [official doc]" +"(https://vllm-ascend.readthedocs.io/en/latest/tutorials/single_npu.html) to " +"run the quick demo. [#709](https://github.com/vllm-project/vllm-ascend/" +"pull/709)" +msgstr "" +"现在已支持 Qwen3 和 Qwen3MOE。请按照[官方文档](https://vllm-ascend." +"readthedocs.io/en/latest/tutorials/single_npu.html)运行快速演示。[#709]" +"(https://github.com/vllm-project/vllm-ascend/pull/709)" + +#: ../../user_guide/release_notes.md:188 +msgid "" +"Ascend W8A8 quantization method is supported now. Please take the [official " +"doc](https://vllm-ascend.readthedocs.io/en/latest/tutorials/" +"multi_npu_quantization.html) for example. Any [feedback](https://github.com/" +"vllm-project/vllm-ascend/issues/619) is welcome. [#580](https://github.com/" +"vllm-project/vllm-ascend/pull/580)" +msgstr "" +"现在支持 Ascend W8A8 量化方法。请参考[官方文档](https://vllm-ascend." +"readthedocs.io/en/latest/tutorials/multi_npu_quantization.html) 示例。欢迎提" +"供任何[反馈](https://github.com/vllm-project/vllm-ascend/issues/619)。[#580]" +"(https://github.com/vllm-project/vllm-ascend/pull/580)" + +#: ../../user_guide/release_notes.md:189 +msgid "" +"DeepSeek V3/R1 works with DP, TP and MTP now. Please note that it's still " +"in experimental status. Let us know if you hit any problem. [#429](https://" +"github.com/vllm-project/vllm-ascend/pull/429) [#585](https://github.com/" +"vllm-project/vllm-ascend/pull/585) [#626](https://github.com/vllm-project/" +"vllm-ascend/pull/626) [#636](https://github.com/vllm-project/vllm-ascend/" +"pull/636) [#671](https://github.com/vllm-project/vllm-ascend/pull/671)" +msgstr "" +"DeepSeek V3/R1 现在已经支持 DP、TP 和 MTP。请注意，目前仍处于实验阶段。如果" +"遇到任何问题，请告知我们。 [#429](https://github.com/vllm-project/vllm-" +"ascend/pull/429) [#585](https://github.com/vllm-project/vllm-ascend/" +"pull/585) [#626](https://github.com/vllm-project/vllm-ascend/pull/626) " +"[#636](https://github.com/vllm-project/vllm-ascend/pull/636) [#671](https://" +"github.com/vllm-project/vllm-ascend/pull/671)" + +#: ../../user_guide/release_notes.md:192 +msgid "" +"ACLGraph feature is supported with V1 engine now. It's disabled by default " +"because this feature rely on CANN 8.1 release. We'll make it available by " +"default in the next release [#426](https://github.com/vllm-project/vllm-" +"ascend/pull/426)" +msgstr "" +"ACLGraph 特性现在已被 V1 引擎支持。它默认是禁用的，因为该特性依赖于 CANN " +"8.1 版本。我们将在下一个版本中默认启用此特性 [#426](https://github.com/vllm-" +"project/vllm-ascend/pull/426)。" + +#: ../../user_guide/release_notes.md:193 +msgid "" +"Upgrade PyTorch to 2.5.1. vLLM Ascend no longer relies on the dev version " +"of torch-npu now. Now users don't need to install the torch-npu by hand. " +"The 2.5.1 version of torch-npu will be installed automatically. [#661]" +"(https://github.com/vllm-project/vllm-ascend/pull/661)" +msgstr "" +"升级 PyTorch 至 2.5.1。vLLM Ascend 现在不再依赖 dev 版本的 torch-npu，用户无" +"需手动安装 torch-npu。torch-npu 的 2.5.1 版本将会自动安装。[#661](https://" +"github.com/vllm-project/vllm-ascend/pull/661)" + +#: ../../user_guide/release_notes.md:196 +msgid "" +"MiniCPM model works now. [#645](https://github.com/vllm-project/vllm-ascend/" +"pull/645)" +msgstr "" +"MiniCPM 模型现在可以使用了。[#645](https://github.com/vllm-project/vllm-" +"ascend/pull/645)" + +#: ../../user_guide/release_notes.md:197 +msgid "" +"openEuler container image supported with `v0.8.4-openeuler` tag and customs " +"Ops build is enabled by default for openEuler OS. [#689](https://github.com/" +"vllm-project/vllm-ascend/pull/689)" +msgstr "" +"openEuler 容器镜像已支持 `v0.8.4-openeuler` 标签，并且 openEuler 操作系统默" +"认启用了自定义 Ops 构建。[#689](https://github.com/vllm-project/vllm-ascend/" +"pull/689)" + +#: ../../user_guide/release_notes.md:198 +msgid "" +"Fix ModuleNotFoundError bug to make Lora work [#600](https://github.com/" +"vllm-project/vllm-ascend/pull/600)" +msgstr "" +"修复 ModuleNotFoundError 错误以使 Lora 正常工作 [#600](https://github.com/" +"vllm-project/vllm-ascend/pull/600)" + +#: ../../user_guide/release_notes.md:199 +msgid "" +"Add \"Using EvalScope evaluation\" doc [#611](https://github.com/vllm-" +"project/vllm-ascend/pull/611)" +msgstr "" +"添加了“使用 EvalScope 评估”文档 [#611](https://github.com/vllm-project/vllm-" +"ascend/pull/611)" + +#: ../../user_guide/release_notes.md:200 +msgid "" +"Add a `VLLM_VERSION` environment to make vLLM version configurable to help " +"developer set correct vLLM version if the code of vLLM is changed by hand " +"locally. [#651](https://github.com/vllm-project/vllm-ascend/pull/651)" +msgstr "" +"新增了一个 `VLLM_VERSION` 环境变量，使 vLLM 版本可以配置，帮助开发者在本地手" +"动修改 vLLM 代码后，设置正确的 vLLM 版本。[#651](https://github.com/vllm-" +"project/vllm-ascend/pull/651)" + +#: ../../user_guide/release_notes.md:202 +msgid "v0.8.4rc1 - 2025.04.18" +msgstr "v0.8.4rc1 - 2025.04.18" + +#: ../../user_guide/release_notes.md:204 +msgid "" +"This is the first release candidate of v0.8.4 for vllm-ascend. Please " +"follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to start " +"the journey. From this version, vllm-ascend will follow the newest version " +"of vllm and release every two weeks. For example, if vllm releases v0.8.5 " +"in the next two weeks, vllm-ascend will release v0.8.5rc1 instead of " +"v0.8.4rc2. Please find the detail from the [official documentation](https://" +"vllm-ascend.readthedocs.io/en/latest/community/versioning_policy." +"html#release-window)." +msgstr "" +"这是 vllm-ascend v0.8.4 的第一个候选发布版本。请按照[官方文档](https://vllm-" +"ascend.readthedocs.io/en/)开始使用。本版本起，vllm-ascend 将跟随 vllm 的最新" +"版本并每两周发布一次。例如，如果 vllm 在接下来的两周内发布 v0.8.5，vllm-" +"ascend 将发布 v0.8.5rc1，而不是 v0.8.4rc2。详细信息请参考[官方文档](https://" +"vllm-ascend.readthedocs.io/en/latest/community/versioning_policy." +"html#release-window)。" + +#: ../../user_guide/release_notes.md:208 +msgid "" +"vLLM V1 engine experimental support is included in this version. You can " +"visit [official guide](https://docs.vllm.ai/en/latest/getting_started/" +"v1_user_guide.html) to get more detail. By default, vLLM will fallback to " +"V0 if V1 doesn't work, please set `VLLM_USE_V1=1` environment if you want " +"to use V1 forcely." +msgstr "" +"本版本包含了对 vLLM V1 引擎的实验性支持。你可以访问[官方指南](https://docs." +"vllm.ai/en/latest/getting_started/v1_user_guide.html)获取更多详细信息。默认" +"情况下，如果 V1 不可用，vLLM 会自动回退到 V0。如果你想强制使用 V1，请设置 " +"`VLLM_USE_V1=1` 环境变量。" + +#: ../../user_guide/release_notes.md:209 +msgid "" +"LoRA、Multi-LoRA And Dynamic Serving is supported now. The performance will " +"be improved in the next release. Please follow the [official doc](https://" +"docs.vllm.ai/en/latest/features/lora.html) for more usage information. " +"Thanks for the contribution from China Merchants Bank. [#521](https://" +"github.com/vllm-project/vllm-ascend/pull/521)." +msgstr "" +"现在已支持 LoRA、Multi-LoRA 和动态服务。性能将在下一个版本中得到提升。请参阅" +"[官方文档](https://docs.vllm.ai/en/latest/features/lora.html)获取更多使用信" +"息。感谢招商银行的贡献。[#521](https://github.com/vllm-project/vllm-ascend/" +"pull/521)。" + +#: ../../user_guide/release_notes.md:210 +msgid "" +"Sleep Mode feature is supported. Currently it's only work on V0 engine. V1 " +"engine support will come soon. [#513](https://github.com/vllm-project/vllm-" +"ascend/pull/513)" +msgstr "" +"已支持休眠模式功能。目前它只在V0引擎上有效，V1引擎的支持即将到来。[#513]" +"(https://github.com/vllm-project/vllm-ascend/pull/513)" + +#: ../../user_guide/release_notes.md:214 +msgid "" +"The Ascend scheduler is added for V1 engine. This scheduler is more " +"affinity with Ascend hardware. More scheduler policy will be added in the " +"future. [#543](https://github.com/vllm-project/vllm-ascend/pull/543)" +msgstr "" +"为V1引擎新增了Ascend调度器。该调度器与Ascend硬件更加适配。未来还将添加更多调" +"度策略。 [#543](https://github.com/vllm-project/vllm-ascend/pull/543)" + +#: ../../user_guide/release_notes.md:215 +msgid "" +"Disaggregated Prefill feature is supported. Currently only 1P1D works. NPND " +"is under design by vllm team. vllm-ascend will support it once it's ready " +"from vLLM. Follow the [official guide](https://docs.vllm.ai/en/latest/" +"features/disagg_prefill.html) to use. [#432](https://github.com/vllm-" +"project/vllm-ascend/pull/432)" +msgstr "" +"支持分离式预填充（Disaggregated Prefill）功能。目前仅支持1P1D，NPND正在由" +"vllm团队设计中。一旦vLLM支持，vllm-ascend将会支持。请按照[官方指南](https://" +"docs.vllm.ai/en/latest/features/disagg_prefill.html)使用。[#432](https://" +"github.com/vllm-project/vllm-ascend/pull/432)" + +#: ../../user_guide/release_notes.md:216 +msgid "" +"Spec decode feature works now. Currently it's only work on V0 engine. V1 " +"engine support will come soon. [#500](https://github.com/vllm-project/vllm-" +"ascend/pull/500)" +msgstr "" +"Spec 解码功能现在可以使用。目前它只在 V0 引擎上工作，对 V1 引擎的支持即将到" +"来。[#500](https://github.com/vllm-project/vllm-ascend/pull/500)" + +#: ../../user_guide/release_notes.md:217 +msgid "" +"Structured output feature works now on V1 Engine. Currently it only " +"supports xgrammar backend while using guidance backend may get some errors. " +"[#555](https://github.com/vllm-project/vllm-ascend/pull/555)" +msgstr "" +"结构化输出功能现在已在V1引擎上生效。目前仅支持xgrammar后端，使用guidance后端" +"可能会出现一些错误。[#555](https://github.com/vllm-project/vllm-ascend/" +"pull/555)" + +#: ../../user_guide/release_notes.md:221 +msgid "" +"A new communicator `pyhccl` is added. It's used for call CANN HCCL library " +"directly instead of using `torch.distribute`. More usage of it will be " +"added in the next release [#503](https://github.com/vllm-project/vllm-" +"ascend/pull/503)" +msgstr "" +"新增了一个通信器 `pyhccl`。它用于直接调用 CANN HCCL 库，而不是使用 `torch." +"distribute`。将在下一个版本中添加更多用法 [#503](https://github.com/vllm-" +"project/vllm-ascend/pull/503)。" + +#: ../../user_guide/release_notes.md:222 +msgid "" +"The custom ops build is enabled by default. You should install the packages " +"like `gcc`, `cmake` first to build `vllm-ascend` from source. Set " +"`COMPILE_CUSTOM_KERNELS=0` environment to disable the compilation if you " +"don't need it. [#466](https://github.com/vllm-project/vllm-ascend/pull/466)" +msgstr "" +"自定义算子的构建默认是启用的。你应该先安装如 `gcc`、`cmake` 等包以便从源码编" +"译 `vllm-ascend`。如果不需要自定义算子的编译，可以设置环境变量 " +"`COMPILE_CUSTOM_KERNELS=0` 来禁用编译。 [#466](https://github.com/vllm-" +"project/vllm-ascend/pull/466)" + +#: ../../user_guide/release_notes.md:223 +msgid "" +"The custom op `rotay embedding` is enabled by default now to improve the " +"performance. [#555](https://github.com/vllm-project/vllm-ascend/pull/555)" +msgstr "" +"自定义算子 `rotay embedding` 现在已默认启用，以提升性能。[#555](https://" +"github.com/vllm-project/vllm-ascend/pull/555)" + +#: ../../user_guide/release_notes.md:225 +msgid "v0.7.3rc2 - 2025.03.29" +msgstr "v0.7.3rc2 - 2025.03.29" + +#: ../../user_guide/release_notes.md:227 +msgid "" +"This is 2nd release candidate of v0.7.3 for vllm-ascend. Please follow the " +"[official doc](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev) to start " +"the journey." +msgstr "" +"这是 vllm-ascend v0.7.3 的第二个候选发布版本。请根据[官方文档](https://vllm-" +"ascend.readthedocs.io/en/v0.7.3-dev)开始使用。" + +#: ../../user_guide/release_notes.md:228 ../../user_guide/release_notes.md:250 +msgid "" +"Quickstart with container: https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/" +"quick_start.html" +msgstr "" +"容器快速入门： https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/quick_start." +"html" + +#: ../../user_guide/release_notes.md:229 ../../user_guide/release_notes.md:251 +msgid "" +"Installation: https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/installation." +"html" +msgstr "" +"安装: https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/installation.html" + +#: ../../user_guide/release_notes.md:232 +msgid "" +"Add Ascend Custom Ops framewrok. Developers now can write customs ops using " +"AscendC. An example ops `rotary_embedding` is added. More tutorials will " +"come soon. The Custom Ops compilation is disabled by default when " +"installing vllm-ascend. Set `COMPILE_CUSTOM_KERNELS=1` to enable it. [#371]" +"(https://github.com/vllm-project/vllm-ascend/pull/371)" +msgstr "" +"新增了Ascend自定义算子框架。开发者现在可以使用AscendC编写自定义算子。新增了" +"一个示例算子 `rotary_embedding` 。更多教程即将发布。安装vllm-ascend时，自定" +"义算子的编译默认是关闭的。可通过设置 `COMPILE_CUSTOM_KERNELS=1` 启用。[#371]" +"(https://github.com/vllm-project/vllm-ascend/pull/371)" + +#: ../../user_guide/release_notes.md:233 +msgid "" +"V1 engine is basic supported in this release. The full support will be done " +"in 0.8.X release. If you hit any issue or have any requirement of V1 " +"engine. Please tell us [here](https://github.com/vllm-project/vllm-ascend/" +"issues/414). [#376](https://github.com/vllm-project/vllm-ascend/pull/376)" +msgstr "" +"本版本对 V1 引擎提供了基础支持，全面支持将在 0.8.X 版本中完成。如果您遇到任" +"何问题或有 V1 引擎的相关需求，请在[这里](https://github.com/vllm-project/" +"vllm-ascend/issues/414)告诉我们。[#376](https://github.com/vllm-project/" +"vllm-ascend/pull/376)" + +#: ../../user_guide/release_notes.md:234 +msgid "" +"Prefix cache feature works now. You can set `enable_prefix_caching=True` to " +"enable it. [#282](https://github.com/vllm-project/vllm-ascend/pull/282)" +msgstr "" +"前缀缓存功能现在已经可用。你可以通过设置 `enable_prefix_caching=True` 来启用" +"该功能。[#282](https://github.com/vllm-project/vllm-ascend/pull/282)" + +#: ../../user_guide/release_notes.md:237 +msgid "" +"Bump torch_npu version to dev20250320.3 to improve accuracy to fix `!!!` " +"output problem. [#406](https://github.com/vllm-project/vllm-ascend/pull/406)" +msgstr "" +"将 torch_npu 版本升级到 dev20250320.3 以提升精度，修复 `!!!` 输出问题。" +"[#406](https://github.com/vllm-project/vllm-ascend/pull/406)" + +#: ../../user_guide/release_notes.md:240 +msgid "" +"The performance of Qwen2-vl is improved by optimizing patch embedding " +"(Conv3D). [#398](https://github.com/vllm-project/vllm-ascend/pull/398)" +msgstr "" +"通过优化 patch embedding（Conv3D），Qwen2-vl 的性能得到了提升。[#398]" +"(https://github.com/vllm-project/vllm-ascend/pull/398)" + +#: ../../user_guide/release_notes.md:244 +msgid "" +"Fixed a bug to make sure multi step scheduler feature work. [#349](https://" +"github.com/vllm-project/vllm-ascend/pull/349)" +msgstr "" +"修复了一个错误，以确保多步调度器功能正常工作。[#349](https://github.com/" +"vllm-project/vllm-ascend/pull/349)" + +#: ../../user_guide/release_notes.md:245 +msgid "" +"Fixed a bug to make prefix cache feature works with correct accuracy. [#424]" +"(https://github.com/vllm-project/vllm-ascend/pull/424)" +msgstr "" +"修复了一个 bug，使前缀缓存功能能够以正确的准确性运行。[#424](https://github." +"com/vllm-project/vllm-ascend/pull/424)" + +#: ../../user_guide/release_notes.md:247 +msgid "v0.7.3rc1 - 2025.03.14" +msgstr "v0.7.3rc1 - 2025.03.14" + +#: ../../user_guide/release_notes.md:249 +msgid "" +"🎉 Hello, World! This is the first release candidate of v0.7.3 for vllm-" +"ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/" +"en/v0.7.3-dev) to start the journey." +msgstr "" +"🎉 你好，世界！这是 vllm-ascend v0.7.3 的第一个候选发布版本。请按照[官方文" +"档](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev)开始你的旅程。" + +#: ../../user_guide/release_notes.md:254 +msgid "" +"DeepSeek V3/R1 works well now. Read the [official guide](https://vllm-" +"ascend.readthedocs.io/en/v0.7.3-dev/tutorials/multi_node.html) to start! " +"[#242](https://github.com/vllm-project/vllm-ascend/pull/242)" +msgstr "" +"DeepSeek V3/R1 现在运行良好。请阅读[官方指南](https://vllm-ascend." +"readthedocs.io/en/v0.7.3-dev/tutorials/multi_node.html)开始！[#242](https://" +"github.com/vllm-project/vllm-ascend/pull/242)" + +#: ../../user_guide/release_notes.md:255 +msgid "" +"Speculative decoding feature is supported. [#252](https://github.com/vllm-" +"project/vllm-ascend/pull/252)" +msgstr "" +"已支持猜测性解码功能。[#252](https://github.com/vllm-project/vllm-ascend/" +"pull/252)" + +#: ../../user_guide/release_notes.md:256 +msgid "" +"Multi step scheduler feature is supported. [#300](https://github.com/vllm-" +"project/vllm-ascend/pull/300)" +msgstr "" +"已支持多步调度器功能。[#300](https://github.com/vllm-project/vllm-ascend/" +"pull/300)" + +#: ../../user_guide/release_notes.md:259 +msgid "" +"Bump torch_npu version to dev20250308.3 to improve `_exponential` accuracy" +msgstr "将 torch_npu 版本升级到 dev20250308.3，以提升 `_exponential` 的精度" + +#: ../../user_guide/release_notes.md:260 +msgid "" +"Added initial support for pooling models. Bert based model, such as `BAAI/" +"bge-base-en-v1.5` and `BAAI/bge-reranker-v2-m3` works now. [#229](https://" +"github.com/vllm-project/vllm-ascend/pull/229)" +msgstr "" +"新增了对池化模型的初步支持。现在支持 Bert 基础模型，如 `BAAI/bge-base-en-" +"v1.5` 和 `BAAI/bge-reranker-v2-m3`。 [#229](https://github.com/vllm-project/" +"vllm-ascend/pull/229)" + +#: ../../user_guide/release_notes.md:263 +msgid "" +"The performance of Qwen2-VL is improved. [#241](https://github.com/vllm-" +"project/vllm-ascend/pull/241)" +msgstr "" +"Qwen2-VL 的性能得到了提升。[#241](https://github.com/vllm-project/vllm-" +"ascend/pull/241)" + +#: ../../user_guide/release_notes.md:264 +msgid "" +"MiniCPM is now supported [#164](https://github.com/vllm-project/vllm-ascend/" +"pull/164)" +msgstr "" +"MiniCPM 现在已被支持 [#164](https://github.com/vllm-project/vllm-ascend/" +"pull/164)" + +#: ../../user_guide/release_notes.md:267 +msgid "" +"Support MTP(Multi-Token Prediction) for DeepSeek V3/R1 [#236](https://" +"github.com/vllm-project/vllm-ascend/pull/236)" +msgstr "" +"为 DeepSeek V3/R1 支持 MTP（多标记预测） [#236](https://github.com/vllm-" +"project/vllm-ascend/pull/236)" + +#: ../../user_guide/release_notes.md:268 +msgid "" +"[Docs] Added more model tutorials, include DeepSeek, QwQ, Qwen and Qwen " +"2.5VL. See the [official doc](https://vllm-ascend.readthedocs.io/en/v0.7.3-" +"dev/tutorials/index.html) for detail" +msgstr "" +"[文档] 增加了更多的模型教程，包括 DeepSeek、QwQ、Qwen 和 Qwen 2.5VL。详情请" +"参见[官方文档](https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/tutorials/" +"index.html)。" + +#: ../../user_guide/release_notes.md:269 +msgid "" +"Pin modelscope<1.23.0 on vLLM v0.7.3 to resolve: https://github.com/vllm-" +"project/vllm/pull/13807" +msgstr "" +"在 vLLM v0.7.3 上锁定 modelscope 版本低于 1.23.0，以解决：https://github." +"com/vllm-project/vllm/pull/13807" + +#: ../../user_guide/release_notes.md:271 ../../user_guide/release_notes.md:302 +msgid "Known issues" +msgstr "已知问题" + +#: ../../user_guide/release_notes.md:272 +msgid "" +"In [some cases](https://github.com/vllm-project/vllm-ascend/issues/324), " +"especially when the input/output is very long, the accuracy of output may " +"be incorrect. We are working on it. It'll be fixed in the next release." +msgstr "" +"在[某些情况下](https://github.com/vllm-project/vllm-ascend/issues/324)，特别" +"是当输入或输出非常长时，输出的准确性可能会有误。我们正在解决这个问题。将在下" +"一个版本中修复。" + +#: ../../user_guide/release_notes.md:273 +msgid "" +"Improved and reduced the garbled code in model output. But if you still hit " +"the issue, try to change the generation config value, such as " +"`temperature`, and try again. There is also a knonwn issue shown below. Any " +"[feedback](https://github.com/vllm-project/vllm-ascend/issues/267) is " +"welcome. [#277](https://github.com/vllm-project/vllm-ascend/pull/277)" +msgstr "" +"改进并减少了模型输出中的乱码问题。但如果你仍然遇到该问题，请尝试更改生成配置" +"的参数，例如 `temperature`，然后再试一次。下面还列出了一个已知问题。欢迎提供" +"任何[反馈](https://github.com/vllm-project/vllm-ascend/issues/267)。[#277]" +"(https://github.com/vllm-project/vllm-ascend/pull/277)" + +#: ../../user_guide/release_notes.md:275 +msgid "v0.7.1rc1 - 2025.02.19" +msgstr "v0.7.1rc1 - 2025.02.19" + +#: ../../user_guide/release_notes.md:279 +msgid "" +"We are excited to announce the first release candidate of v0.7.1 for vllm-" +"ascend." +msgstr "我们很高兴地宣布 vllm-ascend v0.7.1 的第一个候选版本发布。" + +#: ../../user_guide/release_notes.md:281 +msgid "" +"vLLM Ascend Plugin (vllm-ascend) is a community maintained hardware plugin " +"for running vLLM on the Ascend NPU. With this release, users can now enjoy " +"the latest features and improvements of vLLM on the Ascend NPU." +msgstr "" +"vLLM Ascend 插件（vllm-ascend）是一个由社区维护的硬件插件，用于在 Ascend " +"NPU 上运行 vLLM。通过此版本，用户现在可以在 Ascend NPU 上享受到 vLLM 的最新" +"功能和改进。" + +#: ../../user_guide/release_notes.md:283 +msgid "" +"Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/" +"v0.7.1-dev) to start the journey. Note that this is a release candidate, " +"and there may be some bugs or issues. We appreciate your feedback and " +"suggestions [here](https://github.com/vllm-project/vllm-ascend/issues/19)" +msgstr "" +"请参阅[官方文档](https://vllm-ascend.readthedocs.io/en/v0.7.1-dev)开始您的体" +"验之旅。请注意，这是一个候选发布版本，可能会有一些漏洞或问题。我们非常欢迎您" +"在[这里](https://github.com/vllm-project/vllm-ascend/issues/19)提交反馈和建" +"议。" + +#: ../../user_guide/release_notes.md:287 +msgid "" +"Initial supports for Ascend NPU on vLLM. [#3](https://github.com/vllm-" +"project/vllm-ascend/pull/3)" +msgstr "" +"在 vLLM 上初步支持 Ascend NPU。[#3](https://github.com/vllm-project/vllm-" +"ascend/pull/3)" + +#: ../../user_guide/release_notes.md:288 +msgid "" +"DeepSeek is now supported. [#88](https://github.com/vllm-project/vllm-" +"ascend/pull/88) [#68](https://github.com/vllm-project/vllm-ascend/pull/68)" +msgstr "" +"现在已支持 DeepSeek。 [#88](https://github.com/vllm-project/vllm-ascend/" +"pull/88) [#68](https://github.com/vllm-project/vllm-ascend/pull/68)" + +#: ../../user_guide/release_notes.md:289 +msgid "" +"Qwen, Llama series and other popular models are also supported, you can see " +"more details in [here](https://vllm-ascend.readthedocs.io/en/latest/" +"user_guide/supported_models.html)." +msgstr "" +"Qwen、Llama 系列及其他流行的模型也受支持，更多详情可参见[这里](https://vllm-" +"ascend.readthedocs.io/en/latest/user_guide/supported_models.html)。" + +#: ../../user_guide/release_notes.md:293 +msgid "" +"Added the Ascend quantization config option, the implementation will coming " +"soon. [#7](https://github.com/vllm-project/vllm-ascend/pull/7) [#73]" +"(https://github.com/vllm-project/vllm-ascend/pull/73)" +msgstr "" +"新增了 Ascend 量化配置选项，具体实现即将推出。[#7](https://github.com/vllm-" +"project/vllm-ascend/pull/7) [#73](https://github.com/vllm-project/vllm-" +"ascend/pull/73)" + +#: ../../user_guide/release_notes.md:294 +msgid "" +"Add silu_and_mul and rope ops and add mix ops into attention layer. [#18]" +"(https://github.com/vllm-project/vllm-ascend/pull/18)" +msgstr "" +"添加 silu_and_mul 和 rope 操作，并将混合操作加入到 attention 层。 [#18]" +"(https://github.com/vllm-project/vllm-ascend/pull/18)" + +#: ../../user_guide/release_notes.md:298 +msgid "" +"[CI] Enable Ascend CI to actively monitor and improve quality for vLLM on " +"Ascend. [#3](https://github.com/vllm-project/vllm-ascend/pull/3)" +msgstr "" +"[CI] 启用 Ascend CI，主动监测并提升 vLLM 在 Ascend 上的质量。[#3](https://" +"github.com/vllm-project/vllm-ascend/pull/3)" + +#: ../../user_guide/release_notes.md:299 +msgid "" +"[Docker] Add vllm-ascend container image [#64](https://github.com/vllm-" +"project/vllm-ascend/pull/64)" +msgstr "" +"[Docker] 添加 vllm-ascend 容器镜像 [#64](https://github.com/vllm-project/" +"vllm-ascend/pull/64)" + +#: ../../user_guide/release_notes.md:300 +msgid "" +"[Docs] Add a [live doc](https://vllm-ascend.readthedocs.org) [#55](https://" +"github.com/vllm-project/vllm-ascend/pull/55)" +msgstr "" +"[文档] 添加了一个 [在线文档](https://vllm-ascend.readthedocs.org) [#55]" +"(https://github.com/vllm-project/vllm-ascend/pull/55)" + +#: ../../user_guide/release_notes.md:304 +msgid "" +"This release relies on an unreleased torch_npu version. It has been " +"installed within official container image already. Please [install](https://" +"vllm-ascend.readthedocs.io/en/v0.7.1rc1/installation.html) it manually if " +"you are using non-container environment." +msgstr "" +"此版本依赖于尚未发布的 torch_npu 版本。该版本已集成在官方容器镜像中。如果您" +"使用的是非容器环境，请[手动安装](https://vllm-ascend.readthedocs.io/en/" +"v0.7.1rc1/installation.html)。" + +#: ../../user_guide/release_notes.md:305 +msgid "" +"There are logs like `No platform detected, vLLM is running on " +"UnspecifiedPlatform` or `Failed to import from vllm._C with " +"ModuleNotFoundError(\"No module named 'vllm._C'\")` shown when running vllm-" +"ascend. It actually doesn't affect any functionality and performance. You " +"can just ignore it. And it has been fixed in this [PR](https://github.com/" +"vllm-project/vllm/pull/12432) which will be included in v0.7.3 soon." +msgstr "" +"在运行 vllm-ascend 时，会显示类似 `No platform detected, vLLM is running on " +"UnspecifiedPlatform` 或 `Failed to import from vllm._C with " +"ModuleNotFoundError(\"No module named 'vllm._C'\")` 的日志。这实际上不会影响" +"任何功能和性能，你可以直接忽略它。这个问题已在此 [PR](https://github.com/" +"vllm-project/vllm/pull/12432) 中修复，并很快会在 v0.7.3 版本中包含。" + +#: ../../user_guide/release_notes.md:306 +msgid "" +"There are logs like `# CPU blocks: 35064, # CPU blocks: 2730` shown when " +"running vllm-ascend which should be `# NPU blocks:` . It actually doesn't " +"affect any functionality and performance. You can just ignore it. And it " +"has been fixed in this [PR](https://github.com/vllm-project/vllm/" +"pull/13378) which will be included in v0.7.3 soon." +msgstr "" +"在运行 vllm-ascend 时，会显示类似 `# CPU blocks: 35064, # CPU blocks: 2730` " +"的日志，实际应该为 `# NPU blocks:`。这实际上不会影响任何功能和性能，你可以忽" +"略它。该问题已在这个 [PR](https://github.com/vllm-project/vllm/pull/13378) " +"中修复，并将在 v0.7.3 版本中包含。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/index.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/index.po new file mode 100644 index 000000000..040132f9c --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/index.po @@ -0,0 +1,30 @@ +# Translations template for PROJECT. +# Copyright (C) 2025 ORGANIZATION +# This file is distributed under the same license as the PROJECT project. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: PROJECT VERSION\n" +"Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: LANGUAGE \n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/support_matrix/index.md:5 +msgid "Support Matrix" +msgstr "支持矩阵" + +#: ../../user_guide/support_matrix/index.md:1 +msgid "Features and models" +msgstr "特性与模型" + +#: ../../user_guide/support_matrix/index.md:3 +msgid "This section provides a detailed supported matrix by vLLM Ascend." +msgstr "本节提供了 vLLM Ascend 的详细支持矩阵。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_features.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_features.po new file mode 100644 index 000000000..b0bfbbb2f --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_features.po @@ -0,0 +1,264 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/support_matrix/supported_features.md:1 +msgid "Feature Support" +msgstr "功能支持" + +#: ../../user_guide/support_matrix/supported_features.md:3 +msgid "" +"The feature support principle of vLLM Ascend is: **aligned with the vLLM**. " +"We are also actively collaborating with the community to accelerate support." +msgstr "vLLM Ascend 的特性支持原则是：**与 vLLM 保持一致**。我们也在积极与社区合作，加快支持进度。" + +#: ../../user_guide/support_matrix/supported_features.md:5 +msgid "" +"You can check the [support status of vLLM V1 Engine][v1_user_guide]. Below " +"is the feature support status of vLLM Ascend:" +msgstr "你可以查看 [vLLM V1 引擎的支持状态][v1_user_guide]。下面是 vLLM Ascend 的功能支持情况：" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Feature" +msgstr "特性" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "vLLM V0 Engine" +msgstr "vLLM V0 引擎" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "vLLM V1 Engine" +msgstr "vLLM V1 引擎" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Next Step" +msgstr "下一步" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Chunked Prefill" +msgstr "分块预填充" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "🟢 Functional" +msgstr "🟢 功能性" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Functional, see detail note: [Chunked Prefill][cp]" +msgstr "功能性，详见说明：[分块预填充][cp]" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Automatic Prefix Caching" +msgstr "自动前缀缓存" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Functional, see detail note: [vllm-ascend#732][apc]" +msgstr "可用，请参见详细说明：[vllm-ascend#732][apc]" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "LoRA" +msgstr "LoRA" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "[vllm-ascend#396][multilora], [vllm-ascend#893][v1 multilora]" +msgstr "[vllm-ascend#396][multilora]，[vllm-ascend#893][v1 multilora]" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Prompt adapter" +msgstr "提示适配器" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "🔴 No plan" +msgstr "🔴 无计划" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "This feature has been deprecated by vllm." +msgstr "此功能已被 vllm 弃用。" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Speculative decoding" +msgstr "猜测式解码" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Basic support" +msgstr "基础支持" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Pooling" +msgstr "池化" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "🟡 Planned" +msgstr "🟡 计划中" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "CI needed and adapting more models; V1 support rely on vLLM support." +msgstr "需要持续集成（CI）并适配更多模型；V1 的支持依赖于 vLLM 的支持。" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Enc-dec" +msgstr "Enc-dec（编码-解码）" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "🔴 NO plan" +msgstr "🔴 没有计划" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Plan in 2025.06.30" +msgstr "2025.06.30 的计划" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Multi Modality" +msgstr "多模态" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "[Tutorial][multimodal], optimizing and adapting more models" +msgstr "[教程][multimodal]，优化和适配更多模型" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "LogProbs" +msgstr "LogProbs" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "CI needed" +msgstr "需要持续集成（CI）" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Prompt logProbs" +msgstr "提示 logProbs" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Async output" +msgstr "异步输出" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Multi step scheduler" +msgstr "多步调度器" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "🔴 Deprecated" +msgstr "🔴 已弃用" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "[vllm#8779][v1_rfc], replaced by [vLLM V1 Scheduler][v1_scheduler]" +msgstr "[vllm#8779][v1_rfc]，已被 [vLLM V1 调度器][v1_scheduler] 替代" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Best of" +msgstr "精选" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "[vllm#13361][best_of], CI needed" +msgstr "[vllm#13361][best_of]，需要持续集成（CI）" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Beam search" +msgstr "束搜索" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Guided Decoding" +msgstr "引导解码" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "[vllm-ascend#177][guided_decoding]" +msgstr "[vllm-ascend#177][guided_decoding]" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Tensor Parallel" +msgstr "张量并行" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Pipeline Parallel" +msgstr "流水线并行" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Expert Parallel" +msgstr "专家并行" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "CI needed; No plan on V0 support" +msgstr "需要持续集成；没有支持V0的计划" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Data Parallel" +msgstr "数据并行" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "CI needed; No plan on V0 support" +msgstr "需要 CI；暂无 V0 支持计划" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Prefill Decode Disaggregation" +msgstr "预填充 解码 拆分" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "1P1D available, working on xPyD and V1 support." +msgstr "1P1D 已可用，正在开发 xPyD 和 V1 支持。" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Quantization" +msgstr "量化" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "W8A8 available, CI needed; working on more quantization method support" +msgstr "W8A8 已可用，需要持续集成（CI）；正在开发对更多量化方法的支持。" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Graph Mode" +msgstr "图模式" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "🔵 Experimental" +msgstr "🔵 实验性" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Experimental, see detail note: [vllm-ascend#767][graph_mode]" +msgstr "实验性功能，详见说明：[vllm-ascend#767][graph_mode]" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "Sleep Mode" +msgstr "睡眠模式" + +#: ../../user_guide/support_matrix/supported_features.md +msgid "level=1 available, CI needed, working on V1 support" +msgstr "level=1 可用，需要CI，正在开发 V1 支持" + +#: ../../user_guide/support_matrix/supported_features.md:33 +msgid "🟢 Functional: Fully operational, with ongoing optimizations." +msgstr "🟢 功能性：完全可用，正在持续优化中。" + +#: ../../user_guide/support_matrix/supported_features.md:34 +msgid "" +"🔵 Experimental: Experimental support, interfaces and functions may change." +msgstr "🔵 实验性：实验性支持，接口和功能可能会发生变化。" + +#: ../../user_guide/support_matrix/supported_features.md:35 +msgid "🚧 WIP: Under active development, will be supported soon." +msgstr "🚧 WIP：正在积极开发中，很快将会支持。" + +#: ../../user_guide/support_matrix/supported_features.md:36 +msgid "" +"🟡 Planned: Scheduled for future implementation (some may have open " +"PRs/RFCs)." +msgstr "🟡 计划中：已安排将来实现（其中一些可能已有开放的PR/RFC）。" + +#: ../../user_guide/support_matrix/supported_features.md:37 +msgid "🔴 NO plan / Deprecated: No plan for V0 or deprecated by vLLM v1." +msgstr "🔴 没有计划 / 已弃用：V0 没有计划或已被 vLLM v1 弃用。" diff --git a/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_models.po b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_models.po new file mode 100644 index 000000000..8ec780561 --- /dev/null +++ b/docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_models.po @@ -0,0 +1,214 @@ +# SOME DESCRIPTIVE TITLE. +# Copyright (C) 2025, vllm-ascend team +# This file is distributed under the same license as the vllm-ascend +# package. +# FIRST AUTHOR , 2025. +# +#, fuzzy +msgid "" +msgstr "" +"Project-Id-Version: vllm-ascend\n" +"Report-Msgid-Bugs-To: \n" +"POT-Creation-Date: 2025-07-18 09:01+0800\n" +"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" +"Last-Translator: FULL NAME \n" +"Language-Team: zh_CN \n" +"Language: zh_CN\n" +"MIME-Version: 1.0\n" +"Content-Type: text/plain; charset=utf-8\n" +"Content-Transfer-Encoding: 8bit\n" +"Plural-Forms: nplurals=1; plural=0;\n" +"Generated-By: Babel 2.17.0\n" + +#: ../../user_guide/support_matrix/supported_models.md:1 +msgid "Model Support" +msgstr "模型支持" + +#: ../../user_guide/support_matrix/supported_models.md:3 +msgid "Text-only Language Models" +msgstr "纯文本语言模型" + +#: ../../user_guide/support_matrix/supported_models.md:5 +#: ../../user_guide/support_matrix/supported_models.md:38 +msgid "Generative Models" +msgstr "生成模型" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Model" +msgstr "模型" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Supported" +msgstr "支持" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Note" +msgstr "注释" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "DeepSeek v3" +msgstr "DeepSeek v3" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "✅" +msgstr "✅" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "DeepSeek R1" +msgstr "DeepSeek R1" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "DeepSeek Distill (Qwen/LLama)" +msgstr "DeepSeek 精炼（Qwen/LLama）" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Qwen3" +msgstr "Qwen3" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Qwen3-Moe" +msgstr "Qwen3-Moe" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Qwen2.5" +msgstr "Qwen2.5" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "QwQ-32B" +msgstr "QwQ-32B" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "LLama3.1/3.2" +msgstr "LLama3.1/3.2" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Internlm" +msgstr "Internlm" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Baichuan" +msgstr "百川" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Phi-4-mini" +msgstr "Phi-4-mini" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "MiniCPM" +msgstr "MiniCPM" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "MiniCPM3" +msgstr "MiniCPM3" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "LLama4" +msgstr "LLama4" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Mistral" +msgstr "Mistral" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Need test" +msgstr "需要测试" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "DeepSeek v2.5" +msgstr "DeepSeek v2.5" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Gemma-2" +msgstr "Gemma-2" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Mllama" +msgstr "Mllama" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Gemma-3" +msgstr "Gemma-3" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "❌" +msgstr "❌" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "[#496](https://github.com/vllm-project/vllm-ascend/issues/496)" +msgstr "[#496](https://github.com/vllm-project/vllm-ascend/issues/496)" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "ChatGLM" +msgstr "ChatGLM" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "[#554](https://github.com/vllm-project/vllm-ascend/issues/554)" +msgstr "[#554](https://github.com/vllm-project/vllm-ascend/issues/554)" + +#: ../../user_guide/support_matrix/supported_models.md:29 +msgid "Pooling Models" +msgstr "池化模型" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "XLM-RoBERTa-based" +msgstr "基于XLM-RoBERTa" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Molmo" +msgstr "Molmo" + +#: ../../user_guide/support_matrix/supported_models.md:36 +msgid "Multimodal Language Models" +msgstr "多模态语言模型" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Qwen2-VL" +msgstr "Qwen2-VL" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Qwen2.5-VL" +msgstr "Qwen2.5-VL" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "LLaVA 1.5" +msgstr "LLaVA 1.5" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "LLaVA 1.6" +msgstr "LLaVA 1.6" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "[#553](https://github.com/vllm-project/vllm-ascend/issues/553)" +msgstr "[#553](https://github.com/vllm-project/vllm-ascend/issues/553)" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "InternVL2" +msgstr "InternVL2" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "InternVL2.5" +msgstr "InternVL2.5" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Qwen2-Audio" +msgstr "Qwen2-Audio" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "LLaVA-Next" +msgstr "LLaVA-Next" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "LLaVA-Next-Video" +msgstr "LLaVA-Next-Video" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Phi-3-Vison/Phi-3.5-Vison" +msgstr "Phi-3-Vison/Phi-3.5-Vison" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "GLM-4v" +msgstr "GLM-4v" + +#: ../../user_guide/support_matrix/supported_models.md +msgid "Ultravox" +msgstr "Ultravox"