|
|
74f441f4b5
|
[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2025-08-15 10:01:39 -04:00 |
|
|
|
4abfd8796f
|
[V1] [Hybrid] Validate compatibility of attention backend batch reordering at init time (#21557)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
|
2025-08-02 05:29:40 -07:00 |
|
|
|
f81c1bb055
|
[Bugfix] Check NVIDIA artifactory is accessible before using flashinfer cubin kernels (#21893)
|
2025-08-01 08:28:45 -04:00 |
|
|
|
555e7225bc
|
[v1][attention] Support Hybrid Allocator + FlashInfer (#21412)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-07-30 01:45:29 +00:00 |
|
|
|
752c6ade2e
|
[V0 Deprecation] Deprecate BlockSparse Attention & Phi3-Small (#21217)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-07-19 13:53:17 -07:00 |
|
|
|
76b494444f
|
[Attention] Refactor attention metadata builder interface (#20466)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-07-17 04:44:25 +00:00 |
|
|
|
1eb2b9c102
|
[CI] update typos config for CI pre-commit and fix some spells (#20919)
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
|
2025-07-15 21:12:40 -07:00 |
|
|
|
30800b01c2
|
[Nvidia] Integrate SM100 cudnn prefill API to MLA prefill (#20411)
Signed-off-by: Elfie Guo <elfieg@nvidia.com>
Co-authored-by: Elfie Guo <eflieg@nvidia.com>
|
2025-07-15 17:56:45 -07:00 |
|
|
|
8cdc371217
|
SM100 Cutlass MLA decode with unrestricted num_heads (< 128) for DeepSeek TP (#20769)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
|
2025-07-15 01:06:38 +00:00 |
|
|
|
e8cc53af5e
|
[Misc] Log the reason for falling back to FlexAttention (#20699)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-07-14 04:16:51 -07:00 |
|
|
|
5b032352cc
|
[Attention] MLA - Flashinfer Ragged Prefill (#20034)
|
2025-07-10 20:17:47 -07:00 |
|
|
|
9fb52e523a
|
[V1] Support any head size for FlexAttention backend (#20467)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2025-07-06 09:54:36 -07:00 |
|
|
|
a0389e0554
|
[UT][intel GPU] use current_platform instead of device hardcode in v1 tests (#20169)
Signed-off-by: Ma, Liangliang <liangliang.ma@intel.com>
|
2025-07-02 09:06:04 +08:00 |
|
|
|
96453cfa83
|
[BugFix][V1][ROCm] Triton MLA uses V0 backend on V1 engine (#19067)
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
|
2025-07-01 16:12:19 +08:00 |
|
|
|
3597b06a4f
|
[CUDA] Enable full cudagraph for FlashMLA (#18581)
Signed-off-by: luka <luka@neuralmagic.com>
|
2025-06-13 18:12:26 +00:00 |
|
|
|
f98548b9da
|
[torch.compile][ROCm] Fuse quantization onto attention using a torch.compile pass (#16756)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
|
2025-06-12 08:31:04 -07:00 |
|
|
|
41aa578428
|
[NVIDIA] Add Cutlass MLA backend (#17625)
|
2025-06-03 21:40:26 -07:00 |
|
|
|
bdf13965ab
|
[V1] Support cross-layer KV sharing (#18212)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
|
2025-06-03 20:33:07 +00:00 |
|
|
|
02f0c7b220
|
[Misc] Add SPDX-FileCopyrightText (#19100)
Signed-off-by: simon-mo <simon.mo@hey.com>
|
2025-06-03 11:20:17 -07:00 |
|
|
|
ce75efeecb
|
[BugFix] FA2 MLA Accuracy Issue (#18807)
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
|
2025-05-28 08:59:39 +00:00 |
|
|
|
f9c069c85e
|
Modularize fused experts and integrate PPLX kernels (#15956)
|
2025-05-14 13:11:54 -07:00 |
|
|
|
950751a987
|
[v1] Pass BlockTable and KVCacheSpec to AttentionMetadataBuilders (#17483)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-05-10 16:12:04 -07:00 |
|
|
|
5e6f939484
|
[Attention] MLA move rotary embedding to cuda-graph region (#17668)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
|
2025-05-09 11:14:42 +08:00 |
|
|
|
3c9396a64f
|
[FEAT][ROCm]: Support AITER MLA on V1 Engine (#17523)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: qli88 <qiang.li2@amd.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
|
2025-05-09 10:42:05 +08:00 |
|
|
|
cba31c47c4
|
[v1] AttentionMetadata for each layer (#17394)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-05-06 07:58:37 -07:00 |
|
|
|
d6484ef3c3
|
Add full API docs and improve the UX of navigating them (#17485)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-05-03 19:42:43 -07:00 |
|
|
|
afcb3f8863
|
[Attention] MLA move o_proj q_proj into cuda-graph region (#17484)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
|
2025-05-02 03:16:26 +00:00 |
|
|
|
24e6ad3f16
|
[V1] Remove num_input_tokens from attn_metadata (#17193)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
|
2025-04-29 09:28:41 -07:00 |
|
|
|
17eb306fcc
|
[Bugfix] Add contiguous call inside rope kernel wrapper (#17091)
Signed-off-by: 苏政渊 <suzhengyuan@moonshot.cn>
Co-authored-by: 苏政渊 <suzhengyuan@moonshot.cn>
|
2025-04-28 19:24:07 -07:00 |
|
|
|
d8bccde686
|
[BugFix] Fix vllm_flash_attn install issues (#17267)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
|
2025-04-27 17:27:56 -07:00 |
|
|
|
986537f1c3
|
[V1] V1 FlashInfer Attention (#16684)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Aurick Qiao <qiao@aurick.net>
|
2025-04-22 00:38:41 +00:00 |
|
|
|
183dad7a85
|
[Attention] Update to lastest FA3 code (#13111)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
|
2025-04-17 15:14:07 -07:00 |
|
|
|
0377b8310b
|
[MLA] Simplification to batch P/D reordering (#16673)
Signed-off-by: Nick Hill <nhill@redhat.com>
|
2025-04-17 16:12:09 -04:00 |
|
|
|
e9528f6dc6
|
[Kernel] support merge_attn_states CUDA kernel, 3x speedup (#16173)
Signed-off-by: DefTruth <qiustudent_r@163.com>
|
2025-04-11 06:50:50 -06:00 |
|
|
|
04149cce27
|
[BugFix] fix some typos found by typos. (#16314)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
|
2025-04-09 03:43:59 -07:00 |
|
|
|
dccf535f8e
|
[V1] Enable V1 Fp8 cache for FA3 in the oracle (#15191)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-03-23 15:07:04 -07:00 |
|
|
|
91ca929dc7
|
[V1] Fix wrong import path of get_flash_attn_version (#15280)
Signed-off-by: Lehua Ding <lehuading@tencent.com>
|
2025-03-21 03:54:11 -07:00 |
|
|
|
0c6f5023c3
|
[V1] Scheduler Refactoring [1/N] - Add Scheduler Interface (#15250)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
|
2025-03-20 17:50:43 -07:00 |
|
|
|
9532c49836
|
[Attention] MLA get rid of materialization (#14770)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-03-13 23:39:02 -07:00 |
|
|
|
a1c8f3796c
|
dynamic distpatch of fp8 kernels (#14245)
Signed-off-by: Jeff Daily <jeff.daily@amd.com>
|
2025-03-11 10:54:56 -04:00 |
|
|
|
fb0acb6c72
|
[Perf] Improve MLA on V1 (#14540)
Signed-off-by: simon-mo <simon.mo@hey.com>
|
2025-03-10 12:06:58 -07:00 |
|
|
|
db84f5eb3b
|
[Bugfix] DeepSeek Accuracy (#14476)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-03-08 16:47:03 +00:00 |
|
|
|
ca7a2d5f28
|
Revert "[Perf] Reduce MLA CPU overheads in V1 (#14384)" (#14471)
|
2025-03-07 22:18:53 -08:00 |
|
|
|
e1744502c2
|
[FP8] Refactor apply_fp8_linear and apply_fp8_linear_generic into an object (#14390)
Signed-off-by: luka <luka@neuralmagic.com>
|
2025-03-07 05:20:16 +00:00 |
|
|
|
dae6896977
|
[Perf] Reduce MLA CPU overheads in V1 (#14384)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-03-06 19:59:14 -08:00 |
|
|
|
9f1710f1ac
|
Fix mla prefill context performance (#13897)
Signed-off-by: ZhongYingMatrix <zhongyingmatrix@gmail.com>
|
2025-03-06 09:35:49 -08:00 |
|
|
|
f6bb18fd9a
|
[BugFix] MLA + V1, illegal memory access and accuracy issues (#14253)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-03-05 17:10:13 -08:00 |
|
|
|
cf069aa8aa
|
Update deprecated Python 3.8 typing (#13971)
|
2025-03-02 17:34:51 -08:00 |
|
|
|
2e94b9cfbb
|
[Attention] Flash MLA for V1 (#13867)
Signed-off-by: Yang Chen <yangche@fb.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Yang Chen <yangche@fb.com>
|
2025-02-27 23:03:41 +00:00 |
|
|
|
58d1b2aa77
|
[Attention] MLA support for V1 (#13789)
Signed-off-by: Yang Chen <yangche@fb.com>
|
2025-02-27 13:14:17 -05:00 |
|
