xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-25 04:07:56 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,502 Commits 155 Branches 89 Tags
Commit Graph

12502 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Anexdeus
2b03137fca Merge branch 'mlm-full-lora-support' of https://github.com/jeejeelee/vllm into mlm-full-lora-support 2025-12-20 20:40:31 +03:00
bk-201
cb72a0ef01 fix pre-commit 
Signed-off-by: bk-201 <joy25810@foxmail.com>
 2025-12-20 16:36:13 +00:00
bk-201
68116edfe2 fix bug 
Signed-off-by: bk-201 <joy25810@foxmail.com>
 2025-12-20 16:20:12 +00:00
Anexdeus
c6831e793d extended SupportsMultiModal 2025-12-20 17:22:41 +03:00
Anexdeus
cd32aeadfa
Merge branch 'jeejeelee:mlm-full-lora-support' into mlm-full-lora-support 2025-12-20 15:29:40 +03:00
Anexdeus
d525556a25 Revert the mixin changes 2025-12-20 13:31:53 +03:00
Anexdeus
b03d1a04a8 added ProcessingInfoMixin for QwenVL series models 2025-12-20 12:29:46 +03:00
Jee Jee Li
e5ba472ae2
Merge branch 'main' into mlm-full-lora-support 2025-12-20 15:19:28 +08:00
bk-201
4c2e95ad56 correct f-string formatting 
Signed-off-by: bk-201 <joy25810@foxmail.com>
 2025-12-20 06:23:33 +00:00
bk-201
9c9950c080 fix 
Signed-off-by: bk-201 <joy25810@foxmail.com>
 2025-12-20 04:05:59 +00:00
Lucas Wilkinson
ff2168bca3
[CI] FIx fixture 'siglip_attention_config' not found (#31053) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-20 03:46:15 +00:00
Gregory Shtrasberg
0be149524c
[ROCm][CI/Build] Update ROCm dockerfiles (#30991) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-12-20 03:19:12 +00:00
Jee Jee Li
d053aa73e1 Fix 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-12-20 01:47:11 +00:00
zejunchen-zejun
d52c5096d7
[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM attention backend to vllm (#30869) 
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
 2025-12-20 09:03:35 +08:00
Jee Jee Li
463074fac8
Merge branch 'main' into mlm-full-lora-support 2025-12-20 08:25:41 +08:00
Yuxuan Zhang
8a7a414374
GLM-4.7 Tool Parser and Doc Update (#30876) 
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
 2025-12-20 00:09:58 +00:00
Robert Shaw
95befecc18
[MoE Refactor][2/N] Use Modular Kernels for Fp8 (#30825) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-12-19 23:36:38 +00:00
Wentao Ye
4cf9429897
[Bug] Fix error 'Dynamo failed to run FX node with fake tensors for Deepseek V3.2 (#31046) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-19 23:31:31 +00:00
Robert Shaw
83a317f650
[MoE Refactor][3/N] Deprecate cutlass block quant fp8 (b200) (#30990) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-12-19 13:09:54 -08:00
Lucas Wilkinson
5f6477d1d0
[BugFix] Fix TypeError: unhashable type: 'dict' when serving deepseek32 (#30924) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-19 16:07:54 -05:00
Wentao Ye
3bd8335bd0
[Refactor] Refactor for DeepGemmQuantScaleFMT using cache (#30898) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-19 13:50:39 -07:00
Seiji Eicher
1ab5213531
Make engine core client handshake timeout configurable (#27444) 
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
 2025-12-19 20:38:30 +00:00
Zhonghua Deng
969bbc7c61
[Model] Add MiMo-V2-Flash support (#30836) 
Signed-off-by: Abatom <abzhonghua@gmail.com>
Signed-off-by: Jumiar <liuanqim10@126.com>
Signed-off-by: Zyann7 <zyann7@outlook.com>
Co-authored-by: Jumiar <liuanqim10@126.com>
Co-authored-by: Zyann7 <zyann7@outlook.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-12-19 17:17:03 +00:00
bk-201
764aa45140 fix bug 
Signed-off-by: bk-201 <joy25810@foxmail.com>
 2025-12-19 16:57:25 +00:00
Andrey Talman
268a972c62
Update Pytorch version update docs (#30982) 2025-12-19 16:08:53 +00:00
Jinzhen Lin
5fbfa8d9ef
[Quantization] fix marlin w8a8 check (#30961) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
 2025-12-19 07:33:22 -08:00
Shanshan Shen
23a1946e3b
[CustomOp][Refactor] Extract common methods for ApplyRotaryEmb CustomOp (#31021) 
Signed-off-by: shen-shanshan <467638484@qq.com>
 2025-12-19 22:16:09 +08:00
Thomas Parnell
b5545d9d5c
[Bugfix] [Kernel] Triton attention kernels: mask out V blocks that fall outside sliding window (#30887) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-12-19 21:39:54 +08:00
Nishidha Panpaliya
bd2b52fc2d
[CPU][Bugfix] Fix ppc64le CPU build (#30871) 
Signed-off-by: Nishidha Panpaliya <nishidha.panpaliya@partner.ibm.com>
 2025-12-19 12:26:35 +00:00
Li, Jiang
420ba2dbb6
Enable aarch64 CPU performance benchmarks (#26494) 
Signed-off-by: Ioana Ghiban <ioana.ghiban@arm.com>
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Ioana Ghiban <ioana.ghiban@arm.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
 2025-12-19 12:16:18 +00:00
Marko Rosenmueller
455949675d
[Frontend][Bug] allow tool calls in analysis channel (#28139) 
Signed-off-by: Marko Rosenmueller <5467316+dr75@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
 2025-12-19 10:47:44 +00:00
lif
086b96339f
[Bugfix] Add validation for tool requests when tool_parser is unavailable (#30613) 
Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-19 18:23:28 +08:00
Jinzhen Lin
9187de9fac
[Quantization] enable compressed-tensors marlin support for turing (2) (#31008) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
 2025-12-19 08:56:35 +00:00
Isotr0py
ac1c934276
[Bugfix] Fix incorrect tiles creation for mm prefix triton attention (#30974) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-12-19 16:00:33 +08:00
Wenqi Glantz
4924ac582c
Add hidden dimension validation for multimodal embedding inputs (#30968) 
Signed-off-by: Wenqi Glantz <wglantz@nvidia.com>
 2025-12-19 07:59:36 +00:00
Li, Jiang
096b25c9ed
[Doc][CPU] Fix index link for CPU regular release wheels (#31015) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-12-19 07:29:52 +00:00
Jinzhen Lin
de08b8f61b
[Quantization] enable compressed-tensors marlin support for turing (#31000) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
 2025-12-18 20:29:48 -08:00
Nick Hill
2ac85a4544
[BugFix] Fix logprobs with spec decode and modified logits (#30846) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-12-18 19:58:28 -08:00
Andreas Karatzas
7b43db210c
[ROCm][CI][Bugfix] Multi-Modal Model Support Fixes and Attention Backend Improvements (#30270) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2025-12-19 02:17:27 +00:00
PlatinumGod
6a09612b2e
[Bugfix] Fix tool_choice="none" being ignored by GPT-OSS/harmony models (#30867) 
Signed-off-by: yujiepu <pyjapple@gmail.com>
Signed-off-by: PlatinumGod <pyjapple@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
 2025-12-19 09:34:27 +08:00
Nick Hill
45c0526ac9
[BugFix] Handle errors when preprocessing added requests (#30895) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-12-19 01:29:11 +00:00
Benjamin Chislett
d6b3d39b6d
[Cleanup] Refactor FlashInferMetadataBuilder (#29128) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-18 14:45:30 -08:00
Chendi.Xue
6ca74bc11a
[NIXL][BUG FIX] Fix both failing issue and accuracy issue with nixl + host_buffer on CUDA (#30419) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
 2025-12-18 22:10:02 +00:00
Harry Mellor
19c583398a
Check for truthy rope_parameters not the existence of it (#30983) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-18 13:59:10 -08:00
Nick Hill
b0b77c4655
[BugFix] Fix spec decode + structured outputs + preemption edge case (#30916) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-12-18 12:59:55 -08:00
Kayvan Mivehnejad
634a14bd7d
Strengthen input validation and tests for 'parse_raw_prompts’. (#30652) 
Signed-off-by: Kayvan Mivehnejad <K.Mivehnejad@gmail.com>
 2025-12-18 19:51:58 +00:00
Chen Zhang
24b65eff0d
[BugFix] Spec decode with VLLM_ENABLE_V1_MULTIPROCESSING=0 (#30319) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-12-18 19:47:56 +00:00
Elizabeth Thomas
41b6f9200f
Remove all2all backend envvar (#30363) 
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-18 19:46:28 +00:00
Wentao Ye
97000a2be7
[Bug] Fix compressed tensor not using deepgemm (#30820) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-18 14:45:55 -05:00
Isotr0py
d2dc5dfc6e
[Bugfix] Remove tile_size=64 for mm_prefix triton attention (#30973) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-12-18 20:42:32 +01:00