xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 07:24:54 +08:00
Code Issues Packages Projects Releases Wiki Activity
9,814 Commits 155 Branches 89 Tags
Commit Graph

9814 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Lucas Wilkinson
dc464a3d39
[BugFix] AssertionError: Do not capture num_reqs > max_num_reqs for uniform batch (#25505) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-09-23 18:00:29 -06:00
Alexander Matveev
1210e4d95b
[Bugfix] [B200] cutlass_mla - ensure kv_split == 1 for batch size > 1 (#25509) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2025-09-23 16:57:55 -07:00
Lucas Wilkinson
e0b24ea030
[Perf] Increase default max splits for FA3 full cudagraphs (#25495) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-09-23 16:53:34 -07:00
Juan Villamizar
bde2a1a8a4
[ROCm] Small functional changes for gptoss (#25201) 
Signed-off-by: jpvillam <jpvillam@amd.com>
Co-authored-by: jpvillam <jpvillam@amd.com>
 2025-09-23 23:39:50 +00:00
Thomas Parnell
5e25b12236
[Kernel] [Mamba] Remove BLOCK_H=1 from list of tuneable configurations for _chunk_cumsum_fwd_kernel (#25197) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Chih-Chieh-Yang <chih.chieh.yang@ibm.com>
 2025-09-23 23:23:30 +00:00
Corey Lowman
c85d75cf08
Add VLLM_NVTX_SCOPES_FOR_PROFILING=1 to enable nvtx.annotate scopes (#25501) 
Signed-off-by: Corey Lowman <clowman1993@gmail.com>
 2025-09-23 22:50:09 +00:00
kourosh hakhamaneshi
abad204be6
[BugFix] Fix OOM in vLLM replicas by ensuring consistent NCCL memory accounting (#25359) 
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
 2025-09-23 15:49:09 -07:00
Michael Goin
7361ab379f
Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-09-23 22:48:40 +00:00
Andrew Xia
95bc60e4cb
[gpt-oss][bugfix] remove logic to require resp_ in ResponseAPI (#25428) 
Signed-off-by: Andrew Xia <axia@meta.com>
 2025-09-23 15:46:46 -07:00
Michael Goin
4f2954f724
Fix triton_reshape_and_cache_flash.py triton import (#25522) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-09-23 15:26:10 -07:00
rouchenzi
eca7be9077
Add VLLM_ENABLE_INDUCTOR_MAX_AUTOTUNE & VLLM_ENABLE_INDUCTOR_COORDINA… (#25493) 
Signed-off-by: rouchenzi <ruochenwen@gmail.com>
Signed-off-by: rouchenzi <40842833+rouchenzi@users.noreply.github.com>
 2025-09-23 22:17:49 +00:00
Thomas Parnell
969b4da3a6
[V0 Deprecation] Remove placeholder attn (#25510) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-09-23 22:12:14 +00:00
Jialin Ouyang
4f8c4b890a
[Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
 2025-09-23 15:11:14 -07:00
Isotr0py
ae002924e9
[CI/Build] Fix and re-enable v1 PP test on CI (#25496) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-09-23 21:58:25 +00:00
Gregory Shtrasberg
690f948e4a
[Bugfix] Fix for the import error from #24588 (#25481) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-09-23 21:31:08 +00:00
Chauncey
08275ec0a2
[Build] Update Xgrammar to 0.1.25 (#25467) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2025-09-23 21:25:46 +00:00
Alec S
c828d1bf98
[Bugfix] gpt-oss container tool output bug (#25485) 
Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
 2025-09-23 20:43:45 +00:00
Wentao Ye
8b8a8afc89
[CI] Fix Pre-commit Issue (#25497) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-09-24 04:09:37 +08:00
Ilya Markov
8bdd8b5c51
Enable symmetric memory all reduce by default only enabling for TP (#25070) 
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-09-23 15:53:00 -04:00
Michael Goin
a8ffc4f0f2
[Bugfix] Lower gpt-oss max cudagraph size to 992 to be compatible with FA3 (#25508) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-09-23 12:49:55 -07:00
jiahanc
d5944d5146
[Speculators][Speculative Decoding] Fix gpt-oss eagle3 accuracy issue (#25406) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
 2025-09-23 15:44:35 -04:00
Michael Goin
24fab45d96
[Perf] Change default CUDAGraphMode from PIECEWISE to FULL_AND_PIECEWISE (#25444) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-09-23 15:29:26 -04:00
ElizaWszola
63400259d0
[Performance] Move apply_w8a8_block_fp8_linear to an op class (#24666) 
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
 2025-09-23 12:03:10 -07:00
Amir Samani
8c1c81a3de
[core] add nccl symmetric memory for all reduce (#24532) 
Signed-off-by: Amir Samani <asamani@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-09-23 14:33:06 -04:00
Hashem Hashemi
a3a7828010
[ROCm] Add skinny gemm bias support for dtypes fp16,bf16,fp8 (#24988) 
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
Signed-off-by: Hashem Hashemi <159079214+amd-hhashemi@users.noreply.github.com>
 2025-09-23 14:31:45 -04:00
Jee Jee Li
5abb117901
[Core] Ensure LoRA linear respect the base_layer's tp_size and tp_rank (#25487) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-09-23 18:19:25 +00:00
Ekagra Ranjan
867ecdd1c8
[Spec Decode][CI] Add e2e test for examples/spec_decode.py and prevent breaking Acceptance Length (#24531) 
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
 2025-09-23 10:46:40 -07:00
Weida Hong
24e8222745
[Misc] Reduce initialization time of auto_tune (#23682) 
Signed-off-by: Weida Hong <wdhongtw@google.com>
 2025-09-23 17:34:58 +00:00
Burkhard Ringlein
100b630a60
[V1][Kernel] Add triton implementation for reshape_and_cache_flash (#24503) 
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-09-23 12:52:40 -04:00
Ming Yang
527821d191
Use macro guard CUDA functions for back compatibility in grouped_topk_kernel.cu (#25346) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
 2025-09-23 09:45:39 -07:00
Wentao Ye
846197f505
[Log] Optimize kv cache memory log from Bytes to GiB (#25204) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-09-23 12:44:37 -04:00
rivos-shreeasish
2357480b1a
[BugFix] Fix UB in per_token_group_quant.cu (#24913) 
Signed-off-by: Shreeasish Kumar <shreeasish@rivosinc.com>
 2025-09-23 09:14:22 -07:00
bnellnm
f11e3c516b
[Kernels] Support blocked fp8 quantization for compressed tensors MoE (#25219) 
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2025-09-23 16:11:34 +00:00
Harry Mellor
875d6def90
Add backward compatibility for GuidedDecodingParams (#25422) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-09-23 17:07:30 +01:00
Lucas Wilkinson
cc1dc7ed6d
[Core/DBO][2/N] Dual-Batch Overlap add DeepEP High Throughput support and Prefill support (#24845) 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-09-23 16:02:10 +00:00
Thomas Parnell
a903669e10
[V1] Remove V0 code paths for Hybrid models (#25400) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
 2025-09-23 08:26:13 -07:00
Michael Goin
2c58742dff
[UX] Change kv-cache-memory log level to debug (#25479) 
Signed-off-by: Michael Goin <mgoin64@gmail.com>
 2025-09-23 08:01:24 -07:00
Fanli Lin
4c966e440e
[XPU] Fix MOE DP accuracy issue on XPU (#25465) 2025-09-23 14:32:57 +00:00
Peter Pan
da5e7e4329
[Docs] NixlConnector quickstart guide (#24249) 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
Signed-off-by: Peter Pan <peter.pan@daocloud.io>
Signed-off-by: Nicolò Lucchesi<nicolo.lucchesi@gmail.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
 2025-09-23 14:23:22 +00:00
Chauncey
f05a4f0e34
[P/D] Support NIXL connector to disconnect during a clean shutdown (#24423) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
 2025-09-23 16:08:02 +02:00
Joel
61d1b35561
[BugFix] Register expert_map as named buffer for wake_up and sleep (#25458) 
Signed-off-by: wuxibin <wuxibin@bytedance.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-09-23 21:49:13 +08:00
Isotr0py
b6a136b58c
[CI/Build] Fix disabled v1 attention backend selection test (#25471) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-09-23 13:05:46 +00:00
vllmellm
0d9fe260dd
[docs] Benchmark Serving Incorrect Arg (#25474) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-09-23 06:05:11 -07:00
Jee Jee Li
273690a50a
[Core] Optimize LoRA weight loading (#25403) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-09-23 18:19:45 +08:00
Isotr0py
231c2c63e4
[Bugfix] Fix idefics3 tie_word_embeddings (#25454) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-09-23 10:06:48 +00:00
Andreas Hartel
4322c553a6
[Test]: Hermes tool parser stream output error in Qwen3 case (#25203) 
Signed-off-by: Andreas Hartel <andreas.hartel@aleph-alpha.com>
 2025-09-23 17:56:31 +08:00
Cyrus Leung
babad6e5dd
[Misc] Move DP for ViT code inside model executor dir (#25459) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-09-23 09:20:52 +00:00
Zhikaiiii
9383cd6f10
[Frontend] Add a new xml-based tool parser for qwen3-coder (#25028) 
Signed-off-by: Zhikaiiii <1658973216@qq.com>
 2025-09-23 16:07:27 +08:00
Ming Yang
ba8d2165b6
Handle triton kernel import exception (#25319) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-09-23 00:56:00 -07:00
Cyrus Leung
c98be0a232
[Model] Enable DP for ViT in Qwen2-VL (#25445) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-09-23 05:17:10 +00:00