biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
12,835 Commits 2 Branches 140 Tags
ac9f9330e662261242f31f4e0efc9cb9603e4eae
Commit Graph

3709 Commits

Author SHA1 Message Date
Michael Goin
34cd32fe30 [Perf][Kernel] Fused SiLU+Mul+Quant kernel for NVFP4 cutlass_moe (#31832) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
 2026-01-09 07:40:33 -07:00
maang
7cdf7e2fe0 [Model] Remove redundant None check in DeepSeekOCR image input processing (#32016) 
Signed-off-by: maang <maang_h@163.com>
 2026-01-09 06:12:44 -08:00
Xin Yang
e7b68f4d6c [Bugfix] Fix Triton FusedMoE LoRA (#30585) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
 2026-01-09 11:46:59 +00:00
Cyrus Leung
c8ed39b9dd [Model] Reorganize pooling layers (#31973) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-09 11:02:14 +00:00
Alex Brooks
dc77cb7129 [Bugfix] Fix Var Length Batched Padding in Granite Speech (#31906) 
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
 2026-01-09 10:28:43 +00:00
Robert Shaw
0fa8dd24d2 [Bugfix] Fix Typo from NVFP4 Refactor (#31977) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-01-08 16:18:50 -08:00
Robert Shaw
5825bbc1f7 [Quantization] Deprecate Long Tail of Schemes (#31688) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-01-08 19:07:45 -05:00
Yongye Zhu
d62cfe546d [MoE Refactoring][Bugfix]Wrap WNA16 Triton kernel into mk and change compressed tensor kernel selection (#31752) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2026-01-08 19:01:30 -05:00
Lucas Wilkinson
6cdf015c3c [Misc] Fix Current vLLM config is not set. warnings, assert to avoid issues in the future (#31747) 
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>
 2026-01-08 15:20:49 -08:00
Dipika Sikka
5d3b6097ad [Compressed-Tensors] Simplify NVFP4 Conditions, enable marlin support for NVFP4A16 MoEs (#30881) 2026-01-08 17:45:17 -05:00
bnellnm
e74698c27a [Misc][Refactor] Add FusedMoERouter object (#30519) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2026-01-08 20:52:55 +00:00
Michael Goin
87e07a6b46 Revert "feat(moe): Add is_act_and_mul=False support for Triton MoE kernels" (#31978) 2026-01-08 11:31:53 -08:00
danisereb
b8112c1d85 [Bugfix] Fix vllm serve failure with Nemotron Nano V3 FP8 (#31960) 
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
 2026-01-08 16:08:37 +00:00
yxing-bj
fe86be66c5 [Model] Support IQuestCoder model (#31575) 
Signed-off-by: yxing <yxing@iquestlab.com>
 2026-01-08 14:42:57 +00:00
Ce Zhao
1123a87892 [Model] Enable LoRA support for Pixtral (#31724) 
Signed-off-by: <>
Signed-off-by: 赵策 <alcor@zhaocedeMacBook-Air.local>
Signed-off-by: 赵策 <alcor@mac.mynetworksettings.com>
Co-authored-by: 赵策 <alcor@mac.mynetworksettings.com>
 2026-01-08 05:00:57 -08:00
tianshu-Michael-yu
03fd76c570 [Model] Add LFM2-VL model support (#31758) 
Signed-off-by: Tianshu Yu <tianshuyu.formal@gmail.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
 2026-01-08 05:00:27 -08:00
Bijaya Dangol
59d260f5e4 [Model] Add Grok-2 (#31847) 
Signed-off-by: dangoldbj <dangoldbj23@gmail.com>
 2026-01-08 04:59:48 -08:00
Patrick von Platen
18d4e481d0 [Voxtral] Fix speech transcription api (#31388) 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: bk-201 <joy25810@foxmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: prashanth058 <prashanth.dannamaneni@uipath.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: bk-201 <joy25810@foxmail.com>
Co-authored-by: prashanth058 <prashanth.dannamaneni@uipath.com>
Co-authored-by: Anexdeus <5142168@mail.ru>
Co-authored-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
 2026-01-08 18:34:19 +08:00
Isotr0py
2972a05473 [MM Encoder]: Make MMEncoderAttention's scale takes effect properly (#31950) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-08 02:33:48 -08:00
Cyrus Leung
5576227bc1 [Model] Standardize common vision encoders (#31947) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-08 02:33:16 -08:00
Cyrus Leung
d1b6fe007f [Chore] Further cleanup pooler (#31951) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-08 02:16:21 -08:00
omer-dayan
04a49669d1 RayLLM Bugfix - Preserve obj store URL for multi engine_config creation (#30803) 
Signed-off-by: Omer Dayan <omdayan@nvidia.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-08 10:00:25 +00:00
BingjiaWang
96fcd3c267 [Misc] Support qwen3-next lora (#31719) 2026-01-08 09:27:50 +00:00
Isotr0py
eac3b96ec0 [Models] Allow converting Qwen3-VL into Reranker model (#31890) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-08 08:10:15 +00:00
Zyyeric
63baa28cf5 [Model] Enable LoRA support for tower and connector in GLM4-V (#31652) 
Signed-off-by: Zyyeric <eric1976808123@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2026-01-08 15:45:53 +08:00
ShaanveerS
9572f74f15 [Model] Enable LoRA support for tower and connector in DotsOCR (#31825) 
Signed-off-by: ShaanveerS <shaanver.singh@gmail.com>
 2026-01-08 14:50:16 +08:00
Andreas Karatzas
c4041f37a4 [ROCm][LoRA] Fix MoE accuracy regression by preserving float32 router weight scaling (#31931) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-01-08 04:17:56 +00:00
Robert Shaw
9f6dcb71ae [MoE Refactor][16/N] Apply Refactor to NVFP4 (#31692) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Pavani Majety <pmajety@nvidia.com>
 2026-01-08 03:46:27 +00:00
Rabi Mishra
25eef3dc2e feat(moe): Add is_act_and_mul=False support for Triton MoE kernels (#31645) 
Signed-off-by: rabi <ramishra@redhat.com>
 2026-01-08 10:27:09 +08:00
Robert Shaw
5dcd7ef1f2 [MoE Refactor][15/N] Apply Refactor to Fp8 (#31415) 2026-01-07 19:42:33 -05:00
Elvir Crnčević
ffc0a2798b Add back missing DeepEP LL params (#31911) 
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
 2026-01-07 17:47:54 -05:00
Xin Yang
0ada960a20 [Kernel] Support bias type in grouped_topk kernel (#31781) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-07 12:16:32 -08:00
roikoren755
bf184a6621 Enable quantized attention in NemotronH models (#31898) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2026-01-07 17:37:19 +00:00
Cyrus Leung
b7036c87a1 [Refactor] Clean up pooler modules (#31897) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-08 00:07:43 +08:00
Kate Cheng
cc6dafaef2 [Perf][Kernels] Enable FlashInfer DeepGEMM swapAB on SM90 (for W8A8 Linear Op) (#29213) 
Signed-off-by: Kate Cheng <yunhsuanc@nvidia.com>
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
Co-authored-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
 2026-01-07 10:53:54 -05:00
Cyrus Leung
b665bbc2d4 [Chore] Migrate V0 attention utils (#31891) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-07 13:44:36 +00:00
Jared Wen
974138751b [Refactor] GLM-ASR Modeling (#31779) 
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2026-01-07 13:08:29 +00:00
Andy Liu
d111bc53ad [Bugfix][MTP] Fix GLM4 MoE fp8 loading with MTP on (#31757) 
Signed-off-by: Andy Liu <andyliu@roblox.com>
 2026-01-07 09:18:52 +00:00
BlankR
0790f07695 [Misc] Improve error messages for unsupported types and parameters (#30593) 
Signed-off-by: BlankR <hjyblanche@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-01-07 09:00:16 +00:00
maang
1f33e38e81 [Model] Cleanup: Remove redundant manual definition of make_empty_intermediate_tensors in GLM-4-MoE (#31869) 
Signed-off-by: maang <maang_h@163.com>
 2026-01-07 08:18:28 +00:00
weiyu
e7596371a4 [Refactor][TPU] Remove torch_xla path and use tpu-inference (#30808) 
Signed-off-by: Wei-Yu Lin <weiyulin@google.com>
Signed-off-by: weiyu <62784299+weiyu0824@users.noreply.github.com>
 2026-01-07 16:07:16 +08:00
xuebwang-amd
0dd5dee9b9 [Bugfix][Kernel] fix bias adding in triton kernel implemented fused moe (#31676) 
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
 2026-01-07 07:36:13 +00:00
Kevin McKay
4614c5a539 [Bugfix][Hardware][AMD] Consolidate FP8 min/max values helper function (#31106) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Signed-off-by: Kevin McKay <kevin@example.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
 2026-01-07 06:55:03 +00:00
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
482914849c [BugFix] LoRA: Support loading base_layer of experts (#31104) 
Signed-off-by: Hollow Man <hollowman@opensuse.org>
 2026-01-07 14:49:39 +08:00
Jack Yang
0a2c2dc3f1 fixed mypy warnings for files vllm/v1/attention with TEMPORARY workaround (#31465) 
Signed-off-by: Zhuohao Yang <zy242@cornell.edu>
Co-authored-by: Zhuohao Yang <zy242@cornell.edu>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2026-01-07 04:08:47 +00:00
Ce Zhao
a051525e07 [Model] Enable LoRA support for PaliGemma (#31656) 
Signed-off-by: 赵策 <alcor@mac.mynetworksettings.com>
Signed-off-by: Alcor <alcor_zhao@outlook.com>
Co-authored-by: 赵策 <alcor@mac.mynetworksettings.com>
 2026-01-07 10:09:32 +08:00
Li, Jiang
8becf146bd [Quantization][Refactor] Move CPU GPTQ kernel into MP linear (#31801) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Li, Jiang <bigpyj64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-06 19:10:18 +00:00
Yakine Tahtah
4e67a8f616 [Bugfix] Fix GLM-4 MoE router logits dtype for data parallel chunking (#31055) 
Signed-off-by: ReinforcedKnowledge <reinforced.knowledge@gmail.com>
 2026-01-06 17:57:56 +00:00
Vadim Gimpelson
22dffca982 [PERF] Speed-up of GDN attention decode part (Qwen3-Next) (#31722) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
 2026-01-06 17:32:46 +00:00
Jinzhen Lin
2f4bdee61e [Quantization][MoE] remove unused ep logic from moe marlin (#31571) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-01-06 09:07:19 -08:00