biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
14,228 Commits 2 Branches 140 Tags
9d379410179b649f4e7651940debc35c4ac7c0a5
Commit Graph

174 Commits

Author SHA1 Message Date
Wentao Ye
3d2a026fd0 [Feature] Pipeline Parallel Async send/recv, 2.9% E2E throughput improvement (#33368) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2026-02-13 16:38:16 +08:00
Jaewon
4453ba8d9e [Core] Profiler improvements and lazy initialization (#33198) 
Signed-off-by: Jaewon Lee <jaewon@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
 2026-02-12 16:16:38 -08:00
bnellnm
d1481ba783 [MoE Refactor] Introduce MoERunner abstraction and move execution logic from FusedMoE to DefaultMoERunner (#32344) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2026-02-10 19:51:07 -05:00
Ilya Markov
bb2fc8b5e7 [BugFix] Fix async EPLB hang with DeepEP LL all2all backend (#32860) 
Signed-off-by: ilmarkov <markovilya197@gmail.com>
 2026-02-10 22:34:47 +00:00
J Seppänen
506ad7d7c1 [Bugfix] Fix weights offloading for sleep mode (#32947) 
Signed-off-by: Jarno Seppänen <jseppanen@nvidia.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2026-02-10 20:38:17 +00:00
Wentao Ye
67a746e87f [Log] Optimize duplicate startup log (#33944) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-02-06 17:49:56 +00:00
emricksini-h
325ab6b0a8 [Feature] OTEL tracing during loading (#31162) 2026-02-05 16:59:28 -08:00
Aaron Hao
c1858b7ec8 [Feat][RL][1/2] Native Weight Syncing API: NCCL (#31943) 
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Co-authored-by: SumanthRH <sumanthrh99@gmail.com>
 2026-02-05 12:13:23 -05:00
kourosh hakhamaneshi
2f6d17cb2f [rocm][ray] Fix: Unify Ray device visibility handling across CUDA and ROCm (#33308) 
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
 2026-02-04 10:09:14 -08:00
jma99_2333
22d9a056d5 Support clear mm and encoder cache (#33452) 
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2026-01-31 15:22:25 +00:00
Kyle Sayers
f857a03f6b [QeRL] Layerwise Reloading (#32133) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
 2026-01-30 08:50:05 -07:00
Chendi.Xue
8c8ebeb941 [BUGFIX][XPU] fix memory check after XPU reuse GPU_worker (#33358) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
 2026-01-29 09:56:30 -08:00
Nick Hill
6bf3b46d78 [ModelRunner V2] Misc code simplification and cleanup (#33266) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-01-28 14:41:23 -08:00
Reagan Lee
06b557ecd9 feat(benchmark): add encoder forward pass benchmarking to mm-processor (#31655) 
Signed-off-by: Reagan <reaganjlee@gmail.com>
Signed-off-by: Reagan Lee <96998476+reaganjlee@users.noreply.github.com>
Co-authored-by: Hiroken. <105287758+HirokenOvo@users.noreply.github.com>
 2026-01-24 08:24:44 +00:00
Nick Hill
8518b30447 [Model Runner V2] Add KV Connector support (#32742) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-01-23 10:49:17 -08:00
Woosuk Kwon
43fada5360 [Model Runner V2] Refactor dummy_run (#32533) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2026-01-19 14:50:59 -08:00
Shanshan Shen
ce0946249d [Misc] Make mem utils can be reused by other platforms (#32322) 
Signed-off-by: shen-shanshan <467638484@qq.com>
 2026-01-14 03:46:01 -08:00
Max Hu
6ebe34d6fa [Feature] Add iteration level logging and enhance nvtx marker (#31193) 
Signed-off-by: Max Hu <maxhu@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
 2026-01-09 00:13:39 +00:00
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
Nick Hill
a3d909ad2b [Misc] Tidy up some spec decode logic in GPUModelRunner (#31591) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-01-08 09:10:07 -08:00
Ning Xie
c907d22158 [refactor] refactor memory constants usage (#31865) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2026-01-07 18:37:31 +00:00
Cyrus Leung
aafd4d2354 [Chore] Try remove init_cached_hf_modules (#31786) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2026-01-07 12:34:04 +08:00
Ning Xie
6f5e653383 [Log] add log about gpu worker init snapshot and requested memory (#29493) 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
 2026-01-06 17:32:55 +00:00
Wentao Ye
af9a7ec255 [Bug] Revert torch warning fix (#31585) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-01-05 22:31:21 +00:00
wangxiyuan
bb4337b34c [Platform] Deprecate seed_everything (#31659) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2026-01-04 18:34:04 -08:00
Nick Hill
bd877162eb [BugFix] Support online dense model DP without overhead (#30739) 
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: njhill <nickhill123@gmail.com>
 2026-01-02 23:36:38 +08:00
Nick Hill
6c2cfb62ff [BugFix] Fix async scheduling for pooling models (#31584) 
Signed-off-by: njhill <nickhill123@gmail.com>
 2025-12-31 14:48:51 -08:00
Yifan Qiao
52bf066516 [Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166) 
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: KuntaiDu <kuntai@uchicago.edu>
 2025-12-26 18:25:46 -08:00
Michael Goin
8ee90c83f8 Add --max-model-len auto to auto-fit context to available memory (#29431) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-23 21:37:14 -08:00
Boyuan Feng
8dd0db687b [UX] improve profiler error message (#31125) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-12-22 08:45:59 -08:00
Cyrus Leung
2497228ad4 [Chore] Factor out logic for requesting initial memory (#30868) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-17 07:32:17 -08:00
Matthew Bonanni
60dbf7d8f1 Update batch invariant to use attention config (#30704) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-15 15:24:16 -05:00
Lucas Wilkinson
3e41992fec [Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-12 05:57:47 -08:00
Wentao Ye
d6464f2679 [Chore] Fix torch precision warning (#30428) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-11 04:05:56 +00:00
Benjamin Chislett
e858bfe051 [Cleanup] Refactor profiling env vars into a CLI config (#29912) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-09 13:29:33 -05:00
Wentao Ye
83319b44c2 [Compile] Fix torch warning TensorFloat32 tensor cores for float32 matrix multiplication available but not enabled (#29897) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-09 10:40:37 -05:00
Ilya Markov
4e26d3b09e [Compile] Conditional compilation. Introduce compile_ranges (#24252) 
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>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: ProExpertProg <lgovedic@redhat.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>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
 2025-12-05 18:17:32 +00:00
Nick Hill
dc264bcea1 [BugFix] Eagerly abort cancelled final-step requests (#29987) 
Currently, when requests are cancelled while executing their final
step, "completion" is handled based on normal stop processing (e.g.
length or stop token), so the abort has no effect. This is typically
not a problem, but when a kv connector is involved it thinks the
request completed successfully rather than being aborted.

This is problematic for disaggregated prefill which will free kv
cache blocks if the request was aborted but not if it completed
successfully—since the cancelled request will never be sent to
the decode side, kv cache blocks remain pinned until the fall-back
timeout expires. The problem is exacerbated when many requests
are cancelled and/or there are large prefills whose forward pass
takes a long time (since the window is bigger).

This PR fixes the problem by processing pending aborts
immediately prior to processing model output each step; we process
only aborts, not new requests, since it's preferable for latency to
process model outputs before new incoming requests.

Fixes #26400.

Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-12-05 17:28:32 +00:00
Yong Hoon Shin
69520bc695 Add logging for cudagraph related info (#29825) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-12-03 01:01:48 -08:00
Arpit Khandelwal
d7284a2604 [Core] Rename PassConfig flags as per RFC #27995 (#29646) 
Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-12-03 03:38:55 +00:00
Vensen
66b5840287 [Bugfix][sleepmode][fp8 kv cache]: Fix FP8 KV cache + sleep(level=2) gibberish output (#28783) 
Signed-off-by: vensen <vensenmu@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2025-11-30 14:24:25 +08:00
Lucas Wilkinson
56539cddac [Core] Refactor padding logic and pad for CUDA graphs before attention metadata building (#28579) 2025-11-26 14:07:13 -05:00
Woosuk Kwon
30b44a1598 GPU Model Runner V2 (#25266) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
 2025-11-21 08:20:55 -08:00
Wentao Ye
56669c1f29 [CI] Fix mypy for vllm/v1/worker (#29037) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-11-21 11:36:07 +08:00
Benjamin Chislett
fcbcba6c70 [Feat] Iteration-level profiling for Torch and CUDA profiler (#28987) 
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-11-19 19:17:48 -08:00
Julien Denize
cdeec2e606 [BugFix] Ray with multiple nodes (#28873) 
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
 2025-11-19 21:20:58 +00:00
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
Nick Hill
7765e5ba75 [BugFix] Fix PP performance and PP kv connector output regression (#28768) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-11-17 14:08:50 -08:00
Lucia Fang
b316ac6589 [V1] Support MP Executor for multi node distributed inference (#23691) 
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-11-16 09:01:21 +00:00
rasmith
ba041d980b [Log] Save profiler results to file instead of stdout (#28144) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-11-14 23:26:39 +00:00