xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-23 00:25:29 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,170 Commits 155 Branches 89 Tags
Commit Graph

604 Commits

Author SHA1 Message Date
Harry Mellor
cf3eacfe58
Standardise get_rope to use rope_parameters["partial_rotary_factor"], not rotary_dim (#30389) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-11 20:45:23 +00:00
Cyrus Leung
5a87d8b9b1
[Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-10 19:59:35 -08:00
Fadi Arafeh
434ac76a7c
[cpu][ci] Add CPU Attention Tests for Neon Backend (#30347) 
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
 2025-12-10 05:37:35 +00:00
rasmith
b75f826fca
[CI/Build][AMD] Skip quantization kernels tests that require CUTLASS or e4m3fn when not supported by platform (#30020) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-12-10 02:28:37 +00:00
rasmith
7618dc973d
[CI/Build] Make test_mha_attn.py run on correct platform only and check for flash_attn_varlen_func in layer.py (#29145) 2025-12-09 20:18:17 +00:00
Lucas Wilkinson
b37bf51e75
[CI/Test] Fix FP8 per-tensor quant test reference scale shape (#30352) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-09 12:52:20 -06:00
czhu-cohere
f6227c22ab
[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691) 
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
 2025-12-08 19:29:06 -08:00
roikoren755
ae0f69b16a
Add SpecDec support to selective_state_update (#29488) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2025-12-08 16:45:18 -05:00
Daniel Cámpora
184076c3fe
[DeepSeek v3.2] Make top-k work for any logit values. (#27568) 
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-12-08 06:55:58 -08:00
ElizaWszola
af0444bf40
[Performance] Fused blockwise quant RMS norm (#27883) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
 2025-12-07 16:38:04 +00:00
Jinzhen Lin
879ddb09c3
[Kernel][MoE] optimize moe_align_block_size (#29642) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-12-07 01:58:47 -08:00
rasmith
62079d8600
[CI/Build][AMD] Skip marlin, machete, and hadacore tests since these require _C functions not defined for ROCm (#30109) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-12-06 12:54:17 +08:00
Harry Mellor
e10c84e06a
Access partial_rotary_factor from rope_parameters (#29966) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-04 18:42:49 +00:00
bnellnm
2902c34826
[Kernels] Remove BatchedTritonOrDeepGemmExperts and default fallback to Triton (#29929) 
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-12-03 20:49:00 +00:00
Varun Sundar Rabindranath
19bee6d12d
[Performance][DP/EP] Add silu_mul_per_token_group_quant_fp8_colmajor kernel (#29470) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-12-03 18:04:59 +00:00
Omer Ullman Argov
39d28108f4
[Feat] Support non-gated activations in NVFP4 modelopt path (#29004) 2025-11-30 11:02:40 -05:00
Xin Yang
a491b0911b
[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#29708) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
Signed-off-by: Xin Yang <105740670+xyang16@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-30 10:37:25 +08:00
Jinzhen Lin
1656ad3704
[Kernel][Quantization] add w4a8 support for marlin kernel (#24722) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
 2025-11-29 07:19:33 -08:00
Huamin Li
3fd1fb0b60
Revert "[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#28971)" (#29697) 
Signed-off-by: Huamin Li <3ericli@gmail.com>
 2025-11-28 15:26:52 -08:00
Cyrus Leung
33b06a6f24
[Misc] Remove redundant attention var constants (#29650) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-28 04:35:19 -08:00
Xin Yang
745a3bae1a
[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#28971) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-28 10:48:28 +08:00
Matthew Bonanni
430dd4d9eb
[Attention] Remove imports from vllm/attention/__init__.py (#29342) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-11-26 10:53:15 -07:00
Pleaplusone
77e10c9cab
[Perf][Deepseek] optimize gather_and_maybe_dequant_cache kernel's perf for extremely long sequence (#28029) 
Signed-off-by: ganyi <ygan@amd.com>
 2025-11-24 19:05:46 -07:00
bnellnm
8f066146c3
[MoE][Refactor] Make select_experts a non-static method (#29067) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-11-24 13:38:04 -05:00
Roger Wang
0ff70821c9
[Core] Deprecate xformers (#29262) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-11-24 04:18:55 +00:00
rasmith
fd65015a14
[CI/Build] Only use supported types and features on ROCm in MoE kernel tests (#29149) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-11-21 20:34:33 -07:00
rasmith
711241c13c
[CI/Build] Fix illegal memory access and unsupported test in kernels/attention/test_cache.py (#29118) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-11-21 10:58:38 -05:00
rasmith
5e5a7eb16f
[CI/Build] Make test_attention_selector.py run tests on correct platform (#29064) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Signed-off-by: rasmith <Randall.Smith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-20 20:45:56 +00:00
rasmith
3d84ef9054
[CI/Build][AMD] Skip if flash_attn_varlen_func not available in test_aiter_flash_attn.py (#29043) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-11-20 20:39:49 +00:00
Vensen
fb8851f254
[Bugfix][cache_kernels]: Fix OOB in cache_kernels.cu (#28760) 
Signed-off-by: vensen <vensenmu@gmail.com>
Signed-off-by: Vensenmu <vensenmu@gmail.com>
 2025-11-20 02:52:02 -08:00
rasmith
322cb02872
[CI/Build][AMD] Fix import errors in tests/kernels/attention (#29032) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-11-20 17:48:09 +08:00
Alexander Matveev
3aaa94ac99
[Performance] Reduce DeepGEMM N dim restriction from 128 to 64 multiplier (#28687) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-11-19 15:47:13 -08:00
Shu Wang
613abb50d5
[MoE] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#25990) 
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-11-19 13:29:06 -08:00
Ryan Rock
68d7231991
[CI/Build] Fix test_prefix_prefill for AMD (#28905) 
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
 2025-11-19 16:04:36 -05:00
Qiu
2fd893b4ce
[Feature] Prefill Context Parallel (PCP) basic support (#28718) 
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: FENP <yuanyongjie.yyj@antgroup.com>
Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: FENP <yuanyongjie.yyj@antgroup.com>
Co-authored-by: LookAround <lixushi@huawei.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>
Co-authored-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>
 2025-11-19 15:52:44 -05:00
Harry Mellor
a8b70304d6
Update rope_scaling to rope_parameters in preparation for Transformers v5 (#28542) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-11-19 09:06:36 -08:00
Matthew Bonanni
4c23690f43
[Attention] FlashAttention ViT support, make default backend (#28763) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
 2025-11-18 20:06:21 -08:00
Kunshang Ji
2a2d5d2780
Replace torch.cuda.Event with torch.Event for better hardware compatibility (#26985) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-11-18 11:34:36 -08:00
amirkl94
03ee48111d
Feature: Support Relu2 in FusedMoE fp8 cutlass path (#27261) 2025-11-16 13:39:44 -05:00
Cyrus Leung
638e4196d1
[Misc] Make SchedulerConfig.max_model_len init-only (#28733) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-15 01:59:31 -08:00
Varun Sundar Rabindranath
6965ef436f
[Performance][DeepGEMM] Estimate expected_m (#28694) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-11-15 13:52:14 +08:00
Lucas Wilkinson
db56a59970
[BugFix] Fix FA3 IMA with FULL_AND_PIECEWISE and cascade attention (default) (#28702) 2025-11-14 12:19:22 +00:00
Varun Sundar Rabindranath
fe1cd7704d
[Performance][B200] silu_mul_quant: pack scales in int32 (#28358) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-11-13 10:16:55 -08:00
wangxiyuan
2dacd57394
[platform] Move get_cu_count to utils (#27005) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-11-13 08:48:47 +08:00
TJian
edb59a9470
[ROCm] [Bugfix] Fix fused_qknorm_rope_kernel rocm compatibility (#28500) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-11-12 05:01:14 -08:00
Andreas Karatzas
9f0247cfa4
VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
 2025-11-11 18:34:36 -08:00
Li, Jiang
7f829be7d3
[CPU] Refactor CPU attention backend (#27954) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-11-12 09:43:06 +08:00
Zhewen Li
e553424919
[CI/Build] Refactor Attention backend for test_prefix_prefill from xformers to SDPA (#28424) 
Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-11-12 01:09:47 +08:00
zhrrr
68c09efc37
[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) 
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
 2025-11-11 12:00:31 -05:00
bnellnm
a1448b4b69
[Kernels] Split up fused_moe/layer.py, isolate more modular kernel code (#28064) 2025-11-11 07:29:02 -07:00