frozenleaves/vllm-ascend
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm-ascend.git synced 2025-10-20 13:43:53 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
vllm-ascend/vllm_ascend/torchair
History
offline893 6c9909c861 [Patch]patch of v1 executor when enable eplb. (#3511) 
### What this PR does / why we need it?
when using dynamic eplb, patch v1 executor to avoid create child process
failed.

### How was this patch tested?
deepseek in v3.

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: offline0806 <3337230449@qq.com>
Co-authored-by: offline0806 <3337230449@qq.com>
2025-10-19 10:54:26 +08:00
..
models
[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)
2025-10-15 17:48:58 +08:00
ops
[Patch]patch of v1 executor when enable eplb. (#3511)
2025-10-19 10:54:26 +08:00
quantization
[Patch]patch of v1 executor when enable eplb. (#3511)
2025-10-19 10:54:26 +08:00
__init__.py
[1/4][Refactor] Refactor torchair worker (#1885)
2025-07-21 11:50:46 +08:00
torchair_attention.py
[Feat][Graph] Support FULL_DECODE_ONLY mode for GQA/MHA models (#2128)
2025-09-22 17:14:28 +08:00
torchair_mla.py
Fix warning msg print (#3421)
2025-10-15 11:30:30 +08:00
torchair_model_runner.py
Optimize torchair kv_consumer padding logic (#3526)
2025-10-18 16:42:17 +08:00
torchair_sfa.py
[Refactor] Adapt deepseek-v3.2 to vllm 0.11.0 (#3432)
2025-10-15 17:48:58 +08:00
torchair_worker.py
[CI] Upgrade vllm to newest commit (#3182)
2025-09-26 06:18:15 +08:00
utils.py
[Feat] Unquantized Linear to nz and control all nz-cast (#3356)
2025-10-14 17:39:26 +08:00