biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
11,163 Commits 2 Branches 140 Tags
68c09efc37e87032640cf8db571eaf486bd744ac
Commit Graph

3225 Commits

Author SHA1 Message Date
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
Michael Goin
f9a4087182 Remove weight_scale.T special case for SM90 Block FP8 CUTLASS kernel (#28431) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-11-11 11:46:04 -05:00
Fanli Lin
b886068056 [BugFix] Fix RuntimeError in PixtralHFAttention on CPU/XPU (#28444) 
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
 2025-11-11 15:29:33 +00:00
bnellnm
a1448b4b69 [Kernels] Split up fused_moe/layer.py, isolate more modular kernel code (#28064) 2025-11-11 07:29:02 -07:00
Cyrus Leung
afffd3cc8a [Model] Pass mm_features directly into get_mrope_input_positions (#28399) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-11 21:14:48 +08:00
Matthew Bonanni
b30dfa03c5 [Attention] Refactor CUDA attention backend selection logic (#24794) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-11-11 07:40:44 -05:00
Lukas Geiger
9973e6e04a [Model][Qwen3VL] Slighly speedup fast_pos_embed_interpolate (#28434) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-11-11 10:35:10 +00:00
Fanli Lin
c7991269dd [BugFix] 'DeepseekV2Config' object has no attribute 'use_mla'` (#28387) 
Signed-off-by: Lin, Fanli <fanli.lin@intel.com>
 2025-11-11 08:45:38 +00:00
Jiangyun Zhu
f0359fffa4 [Bugfix] fix qwen3-next crash (#28202) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-11-11 08:24:28 +00:00
Roger Wang
4fd4b743a2 [Bugfix] Fix max image size for PaddleOCR-VL (#28442) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2025-11-11 08:07:24 +00:00
Robert Shaw
e605e8e323 [Bugfix] Fix Stream Sync for Shared Expert Overlap (#28430) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
 2025-11-11 05:59:08 +00:00
Wentao Ye
de540c0354 [Feature] Add env var VLLM_MOE_USE_DEEP_GEMM (#28422) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-11-11 02:29:48 +00:00
Wentao Ye
35d801f13f [Feature] Refactor batch invariant fp8 DeepGEMM (#27606) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-11-11 00:08:40 +00:00
Ilya Markov
d17ecc6b19 [PERF] Allreduce fusion. Support torch native matching. Tuning of the thresholds (#24248) 
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2025-11-10 18:33:11 -05:00
Yong Hoon Shin
021143561f [ROCm] Add missing gemm_a8w8_blockscale import (#28378) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-11-10 23:13:36 +00:00
Lucas Wilkinson
6dec9f6109 [BugFix] Fix DeepGEMM over-allocating workspace (#28254) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-11-10 17:01:17 -05:00
Sage Moore
40d33264c6 [Bugfix][EPLB] Disabled shared expert overlap when EPLB is enabled (#28377) 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Sage Moore <sagemoore@utexas.edu>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-11-10 20:39:19 +00:00
jiahanc
34553b9d27 [Performance] Support FP8 flashinfer TRTLLM MOE on Qwen3 and Qwen-3next (#27492) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
 2025-11-10 12:34:57 -05:00
Varun Sundar Rabindranath
b039bfda8f [Bugfix] Fix persistent_masked_m_silu_mul_quant tests (#28366) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-11-10 09:21:52 -08:00
Cyrus Leung
d0e186c16f [V0 Deprecation] Remove unused context_len and seq_len from M-RoPE (#28395) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-11 00:30:06 +08:00
vllmellm
f080a83511 [RFC][ROCm][AITER] Keep all AITER kernels in _aiter_ops class like _custom_ops and _ipex_ops (#24490) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-11-10 08:20:53 -08:00
zejunchen-zejun
b06b9470ca [Rocm][fused_moe][fp4] view weight to torch.float4_e2m1fn_x2 when running aiter fused moe for fp4 model (#27474) 
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
 2025-11-10 10:38:56 -05:00
Ferrebo
912744d066 [Fix] optimize visual token mask with caching and multi-token support (#28374) 
Signed-off-by: Ferrebo <itachi971009@gmail.com>
Signed-off-by: kebo01 <kebo01@baidu.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-10 13:23:49 +00:00
Yu Jiaqi
15be507c86 [bugfix] fix siglip batch text output error (#28365) 
Signed-off-by: piood <2477084691@qq.com>
 2025-11-10 21:21:15 +08:00
Xiake Sun
03fa4d3fb3 [Hardware][AMD][Model] Add Triton MoE tuning support and optimized configs for Qwen3 omni for MI308X (#28373) 
Signed-off-by: Xiake Sun <xiake.sun@amd.com>
Signed-off-by: Xiake Sun <xisun@amd.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-10 04:53:40 +00:00
Jiangyun Zhu
c4768dcf47 [Kernel] Fix fused_gdn_gating (#28343) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-11-09 14:26:35 -07:00
Jiangyun Zhu
7ae5a5fb11 [Misc] Add some comments in qwen3-next (#28267) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-11-08 23:59:24 -08:00
Yong Hoon Shin
de2b78305f [ROCm] Add env to enable/disable aiter triton gemm (#28321) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-11-08 22:27:00 -08:00
Mohammad Miadh Angkad
404d7a9d14 [Performance][gpt-oss] Revert gpt-oss max cudagraph size to 1024 (#28345) 
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
 2025-11-08 15:50:10 -07:00
Robert Shaw
26990d25dc [Bugfix] Update device name for H200 detection (#28349) 
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
 2025-11-08 19:01:11 +00:00
Isotr0py
934a9c3b79 [Model] Consolidate Deepseek-MoE implementation with DeepSeek-v2 (#28101) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-11-08 05:01:27 +00:00
Michael Goin
0852527647 [Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-11-07 18:20:55 -08:00
Kunshang Ji
1aaecda078 [XPU] Enable Expert parallel for MoE models (#28263) 
Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2025-11-08 00:33:11 +00:00
Pavani Majety
72b1c2ae2c [Bugfix] Use latency MOE backend as default for Flashinfer and other misc fixes (#27439) 
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
 2025-11-07 04:18:39 -08:00
Lukas Geiger
e0919f331d [Core][MM] Add mechanism to configure multimodal fields which should stay on CPU (#28168) 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
 2025-11-07 12:14:29 +00:00
Kevin H. Luu
8e19d470af [fix] Revert "fixing mm placeholder replacement issue with gemma3" (#28285) 
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
 2025-11-07 12:09:09 +00:00
Mengqing Cao
1958bda9b4 [Misc][Model][Refactor] Pass the prefix into Linear layers (#28259) 
Signed-off-by: MengqingCao <cmq0113@163.com>
 2025-11-07 19:38:38 +08:00
smit kadvani
11fd69dd54 [amd][gptoss] Perf gain because of block alignment (#28024) 
Signed-off-by: Smit Kadvani <smit.kadvani@gmail.com>
Co-authored-by: Smit Shaileshbhai Kadvani <kadvani@meta.com>
 2025-11-07 05:27:42 +00:00
Harry Mellor
c0a4b95d64 Fix issues from #28242 (#28257) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-11-07 04:23:17 +00:00
Lucas Kabela
4bf56c79cc [Multimodal][torch.compile] Add compilation config field for turning off ViT/MM compile (#28242) 
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
 2025-11-07 00:16:03 +00:00
Aleksandr Malyshev
449de9001a [ROCm] triton fp8 kernel (#27058) 
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
 2025-11-06 14:46:44 -05:00
Julien Denize
7a8375f8a0 Add llama 4 scaling support (#28145) 
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
 2025-11-06 18:55:17 +00:00
Eric Yue
0370679ce9 [Kernel][Model] Tune fused_moe Triton configs for MiniMax-M2 on H100 (#28200) 
Signed-off-by: minatoaquaMK2 <jiacheng.yue@foxmail.com>
 2025-11-06 07:29:46 -08:00
xiangze-arm
c757a15f0f [CPU]Improve cpu fused moe perf (#27244) 
Signed-off-by: Zhang Xiangze <Xiangze.Zhang@arm.com>
 2025-11-06 11:04:18 +00:00
Seungduk Kim
201dc98acc Fix hard-coded parameter name in gemma3n.py (#27946) 
Signed-off-by: Seungduk Kim <seungduk.kim@yanolja.com>
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
 2025-11-05 23:07:36 -08:00
Xiaozhu Meng
e31946f86e [flashinfer] fix FI all2all with FI cutlass moe (#28166) 
Signed-off-by: Xiaozhu <mxz297@gmail.com>
 2025-11-06 05:52:16 +00:00
Isotr0py
43ecd0a900 [Chore] Clean up deepseek v2/v3 config copy (#28055) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-11-06 03:46:30 +00:00
Wentao Ye
d71af5f502 [Feature] Enable TP + EP shared_experts overlap with router, 3.7% E2E performance improvement (#28164) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-11-05 17:21:08 -08:00
Vadim Gimpelson
b6a248bdd7 [PERF] Decouple projections from GDN custom op. Attempt 2 (#28083) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
 2025-11-05 17:01:12 -08:00
wang.yuqi
802748bddb [Bugfix] Fix Qwen3-Reranker-8B load (#28117) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-11-05 18:33:50 +00:00