biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
11,141 Commits 2 Branches 140 Tags
9b24cf6f47124d316a604b7a6f6b61e0e1d7112d
Commit Graph

11141 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Qiu
9b24cf6f47 [bugfix] correct local_chunk_len for DCP in reorg_kvcache with long context (#28526) 
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
(cherry picked from commit 968060c15a)
 2025-11-15 21:54:19 -08:00
Nick Hill
facbc2c21e [BugFix] Ensure EngineArgs.create_engine_config is idempotent (#28515) 
Signed-off-by: Nick Hill <nhill@redhat.com>
(cherry picked from commit 327c0a9a23)
 2025-11-15 21:54:15 -08:00
Roger Wang
e2fd9a2edf [Misc] Turn off encoder torch compile by default (#28634) 
Signed-off-by: Roger Wang <hey@rogerw.io>
(cherry picked from commit d3387750f1)
 2025-11-15 21:54:05 -08:00
Huy Do
1326f17492 Use official xformers-0.0.33 built for PT 2.9 (#28600) 
Signed-off-by: Huy Do <huydhn@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
(cherry picked from commit c33b87e777)
 2025-11-15 21:53:04 -08:00
Harry Mellor
caf412e593 Skip models that cannot currently init on Transformers v5 (#28471) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit 51c599f0ec)
 2025-11-15 21:52:58 -08:00
Harry Mellor
a035b5cffb [CI] Skip "Multi-Modal Models Test (Extended) 3" test that's broken in current Transformers (#28559) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit a39dd7bb06)
 2025-11-15 21:52:46 -08:00
Harry Mellor
5b4dcecdd7 Remove deprecated fields from CompilationConfig (#27593) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
(cherry picked from commit a742134cc5)
 2025-11-15 21:48:13 -08:00
Isotr0py
609bb244bd [Performance] Cache loaded custom logitsprocs to avoid overheads (#28462) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
(cherry picked from commit 3f770f4427)
 2025-11-15 21:44:19 -08:00
Roger Wang
3a9ea77c35 [Bugfix] Fix max image size for PaddleOCR-VL (#28442) 
Signed-off-by: Roger Wang <hey@rogerw.io>
(cherry picked from commit 4fd4b743a2)
 2025-11-15 21:44:19 -08:00
Robert Shaw
28a82bb5e6 [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>
(cherry picked from commit e605e8e323)
 2025-11-15 21:44:19 -08:00
Michael Goin
2a21f3e7c2 Only register rocm_aiter_ops if aiter is found (#28428) 
Signed-off-by: mgoin <mgoin64@gmail.com>
(cherry picked from commit f2d9ad0620)
 2025-11-15 21:36:19 -08:00
Lucas Wilkinson
ab625ba2fc [CI/Test Fix] Fix CP tests on Blackwell (#28404) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
(cherry picked from commit 39029d5192)
 2025-11-15 21:36:19 -08:00
Wentao Ye
324c8cbd79 [Feature] Refactor batch invariant fp8 DeepGEMM (#27606) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
(cherry picked from commit 35d801f13f)
 2025-11-15 21:35:58 -08:00
Adrian Abeyta
75ecaf48fe [Bugfix] Ensure calculated KV scales are applied in attention. (#27232) 
Signed-off-by: adabeyta <aabeyta@redhat.com>
(cherry picked from commit a5a790eea6)
 2025-11-15 21:33:58 -08:00
Robert Shaw
30700b1cd7 [CI] Fix Plugin Tests Tests (#28413) 
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
v0.11.1rc6 		2025-11-10 22:36:11 +00:00
Andrew Xia
4b94ed8f92 [Frontend][2/n] remove empty content from _parse_tool_calls_from_content (#28331) 
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
 2025-11-10 14:07:49 -08:00
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
Wei Wei
bf6a3d0ff5 [Misc] Add more scoping for improved trace (#28329) 
Signed-off-by: Wei Wei <wwei6@meta.com>
 2025-11-10 21:03:21 +00:00
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
Jonas M. Kübler
9c84ca8293 [FA/Chore] Bump FA version for FP8 two-level accumulation (#27889) 
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
 2025-11-10 12:06:04 -08:00
Rémi Delacourt
6d54336ae5 [Bugfix] Fix llguidance backend, rollback when EOS was encountered (#25905) 
Signed-off-by: Rémi Delacourt <remi@mistral.ai>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
 2025-11-10 14:53:32 -05:00
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
caozuoba
40e2eeeb92 [Kernel] Optimization of the mm_k operator. (#28280) 
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-11-10 16:03:46 +00:00
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
TJian
4673e465ff Add @tjtanaa to codeowner for ROCm and multi-modal (#28360) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-11-10 21:39:17 +08:00
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
Mark McLoughlin
6f7de33bed [Metrics] Refactor LoRA state tracking (#26801) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
 2025-11-10 16:34:36 +08:00
Shinichi Hemmi
a98cc35c34 Restore PlaMo2 unit test as pfnet/plamo-2-1b now supports transformers >=4.56 (#28019) 
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
 2025-11-10 06:50:02 +00:00
Lucas Wilkinson
e8697faf03 [V0 deprecation] Remove no longer used get_metadata_cls (#28370) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-11-10 14:32:09 +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
Varun Sundar Rabindranath
6b2b9fd934 [CI] lora/test_mixtral.py : Add additional expected outputs due to flakiness (#28322) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-11-10 10:45:29 +08:00
JartX
c5f685b3ae [ROCm][Platform] Add RX7900XTX device id in _ROCM_DEVICE_ID_NAME_MAP (#28279) 
Signed-off-by: JartX <sagformas@epdcenter.es>
 2025-11-09 23:09:36 +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
Zhewen Li
a65a934ebe [CI/Build] Temporary fix to LM Eval Small Models (#28324) 
Signed-off-by: zhewenli <zhewenli@meta.com>
 2025-11-09 21:08:38 +00:00
usberkeley
4a8d6bd168 Fix cu_num_generated_tokens slicing logic in LogprobsLists.slice() method (#28214) 
Signed-off-by: Bradley <bradley.b.pitt@gmail.com>
 2025-11-09 19:11:46 +00:00
Lucas Wilkinson
636efd10a5 [Core] Separate out attention metadata building logic from prepare inputs (#26764) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-11-09 13:51:43 -05:00
Nick Hill
289eb6c537 [Core] Simplify async KV output aggregation (#28327) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-11-09 09:44:13 -08:00
Nicolò Lucchesi
19d91ece4b [CI] Fix flaky test_eagle_correctness test (#28364) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-11-09 16:04:59 +00:00
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
Ning Xie
e5e9067e61 [Misc] fix typo and add detailed log (#28178) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2025-11-09 05:33:46 +00:00
yihong
3a7d580343 fix: close issue 28338 by fixed python version (#28339) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2025-11-09 05:07:26 +00:00
Kevin H. Luu
05f8d69077 [chore] Move some wikimedia images to S3 (#28351) 
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
 2025-11-09 01:58:26 +00:00
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
ElizaWszola
171133f929 [Bugfix] Fix test fused quant layernorm tests (#27865) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-11-08 14:31:33 -08:00
Cole Murray
32787d0644 Remove setuptools upper bound constraint (<80) (#28337) 
Signed-off-by: Cole Murray <colemurray.cs@gmail.com>
 2025-11-08 22:30:18 +00:00