xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 02:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity
10,031 Commits 155 Branches 89 Tags
Commit Graph

10031 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Benjamin Chislett
177c37e960 [Spec Decode] Enable FlashInfer Spec Decoding (#25196) 
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: lhsjohn <huashuoli@tencent.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Yong Hoon Shin
0e54bbe108 [KV sharing] Re-land Gemma3n model changes from #22628 (#24357) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Nikhil Gupta
6b87ce2ecd [fix]: add Arm 4bit fused moe support (#23809) 
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Lucas Wilkinson
a986f17028 [BugFix] Fix MLA assert with CUTLASS MLA (#25478) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Wentao Ye
faa58fa791 [Compile] Fix AMD Compile Error (#25518) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Kyle Sayers
4ed6b67da3 [Core] Support weight_loader_v2 for UnquantizedLinearMethod (#23036) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Benjamin Chislett
cb825af948 [Bugfix] Use a separate FlashInfer workspace buffer for trtllm-gen (#25520) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
baxingpiaochong
342d17fb7f [V1][Metrics] Add per-request TPOT histogram (#24015) 
Signed-off-by: baxingpiaochong <771405853@qq.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
0xNullPath
3c62d28bb9 [Model] Support SeedOss Reason Parser (#24263) 
Signed-off-by: Yan Lu <luyan@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
ahao-anyscale
9596fbd6e5 [BUG] Allows for RunAI Streamer and Torch.compile cache to be used together (#24922) 
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Wentao Ye
03585bc79d [Bug] Fix AttributeError: 'FusedMoE' object has no attribute 'w13_weight_scale'. Did you mean: 'w13_weight_scale_inv' (#25519) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Chenxi Yang
770cb2e1f8 Add CUTLASS FP8 MOE benchmark scripts and kernel config (#25302) 
Signed-off-by: Chenxi Yang <cxyang@fb.com>
Co-authored-by: Chenxi Yang <cxyang@fb.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Doug Smith
b50fa00537 Improve output when failing json.loads() on structured output test (#25483) 
Signed-off-by: dougbtv <dosmith@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Lucas Wilkinson
8e6a5e7dd4 [BugFix] AssertionError: Do not capture num_reqs > max_num_reqs for uniform batch (#25505) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Alexander Matveev
faae7a7eab [Bugfix] [B200] cutlass_mla - ensure kv_split == 1 for batch size > 1 (#25509) 
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Lucas Wilkinson
d562c2ea09 [Perf] Increase default max splits for FA3 full cudagraphs (#25495) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Juan Villamizar
81ee45298d [ROCm] Small functional changes for gptoss (#25201) 
Signed-off-by: jpvillam <jpvillam@amd.com>
Co-authored-by: jpvillam <jpvillam@amd.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Thomas Parnell
d12433adfc [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Corey Lowman
4ebc513fc1 Add VLLM_NVTX_SCOPES_FOR_PROFILING=1 to enable nvtx.annotate scopes (#25501) 
Signed-off-by: Corey Lowman <clowman1993@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
kourosh hakhamaneshi
7a8f0a3548 [BugFix] Fix OOM in vLLM replicas by ensuring consistent NCCL memory accounting (#25359) 
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Michael Goin
907bbca7b7 Remove redundant mutates_args and dispatch_key for direct_register_custom_op (#25512) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Andrew Xia
eb1f43bc82 [gpt-oss][bugfix] remove logic to require resp_ in ResponseAPI (#25428) 
Signed-off-by: Andrew Xia <axia@meta.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Michael Goin
99eaeebe66 Fix triton_reshape_and_cache_flash.py triton import (#25522) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
rouchenzi
715e24e1b3 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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Thomas Parnell
cf0e250200 [V0 Deprecation] Remove placeholder attn (#25510) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Jialin Ouyang
0c11617ff1 [Core] Use KVCacheBlock as much as possible instead of dict[block_id, KVCacheBlock] (#24830) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Isotr0py
930e691c65 [CI/Build] Fix and re-enable v1 PP test on CI (#25496) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Gregory Shtrasberg
c0f11557e1 [Bugfix] Fix for the import error from #24588 (#25481) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Chauncey
0438c65376 [Build] Update Xgrammar to 0.1.25 (#25467) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Alec S
d8fda7420a [Bugfix] gpt-oss container tool output bug (#25485) 
Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Wentao Ye
86e5b73d71 [CI] Fix Pre-commit Issue (#25497) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Ilya Markov
e49561cd91 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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Michael Goin
0e30643147 [Bugfix] Lower gpt-oss max cudagraph size to 992 to be compatible with FA3 (#25508) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
jiahanc
8ba3b17cc1 [Speculators][Speculative Decoding] Fix gpt-oss eagle3 accuracy issue (#25406) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Michael Goin
8222e2651d [Perf] Change default CUDAGraphMode from PIECEWISE to FULL_AND_PIECEWISE (#25444) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
ElizaWszola
b672b8c3b8 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Amir Samani
56201cfb01 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Hashem Hashemi
9689be1e8e [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Jee Jee Li
65c4513ad8 [Core] Ensure LoRA linear respect the base_layer's tp_size and tp_rank (#25487) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Ekagra Ranjan
5acda4cc71 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Weida Hong
78f892c373 [Misc] Reduce initialization time of auto_tune (#23682) 
Signed-off-by: Weida Hong <wdhongtw@google.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Burkhard Ringlein
26da2c6244 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Ming Yang
0081c6956a 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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Wentao Ye
6462feef65 [Log] Optimize kv cache memory log from Bytes to GiB (#25204) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
rivos-shreeasish
e9a74500e5 [BugFix] Fix UB in per_token_group_quant.cu (#24913) 
Signed-off-by: Shreeasish Kumar <shreeasish@rivosinc.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
bnellnm
02a3ce2230 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Harry Mellor
9cae377a16 Add backward compatibility for GuidedDecodingParams (#25422) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Lucas Wilkinson
8c5c35c027 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Thomas Parnell
f97da2c732 [V1] Remove V0 code paths for Hybrid models (#25400) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00
Michael Goin
02134245a9 [UX] Change kv-cache-memory log level to debug (#25479) 
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:54 -07:00