xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-25 01:15:01 +08:00
Code Issues Packages Projects Releases Wiki Activity
10,082 Commits 155 Branches 89 Tags
Commit Graph

10082 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Michael Goin
173c8a9520 [CI/Build] Conditionally register cutlass_fp4_group_mm to fix building on Hopper (#26138) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:58 -07:00
Matthew Bonanni
2ea7d48656 [Attention] Move Backend enum into registry (#25893) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:58 -07:00
Ekagra Ranjan
8db7b7f39c [Bug][Benchmark] Fix duplicate req in oversampling (#26140) 
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 13:35:58 -07:00
Wentao Ye
587b30c571 [Log] Optimize DeepGEMM Missing Log (#26106) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:58 -07:00
Michael Goin
0c76bb2de1 [Bugfix] Disable cascade attention with FlashInfer (#26130) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.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 13:35:58 -07:00
Matthew Bonanni
72c5dd0310 Fix MTP with deepep_low_latency (#25904) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:58 -07:00
ElizaWszola
abc55b1fe5 [Perf] Fix and reapply move apply w8a8 block fp8 linear to class (#25696) 
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 13:35:58 -07:00
Chen Zhang
d737c66b95 [Mamba][KVCacheManager] Simplify kv cache manage logic for mamba + MTP (#25119) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:58 -07:00
Ekagra Ranjan
da3a188bdb EAGLE 3: Fix preamble so that measured speedup over Eagle 1 becomes 32% instead of 5% on MTBench (#25916) 
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:58 -07:00
Chen Zhang
77e958752b [Deepseek v3.2] Support indexer prefill chunking (#25999) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Chenheli Hua
c5880cfa4c [Small] Prevent bypassing media domain restriction via HTTP redirects (#26035) 
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucas Wilkinson
01888b5cbf [BugFix] Fix FI accuracy issue when used for MLA prefill (#26063) 
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>
Co-authored-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Cyrus Leung
fa179abde3 [CI/Build] Replace vllm.entrypoints.openai.api_server entrypoint with vllm serve command (#25967) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Michael Goin
5c8a4a2208 [CI] Add Blackwell DeepSeek FP8 FlashInfer MoE tests (#26040) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
vllmellm
06d102ecc8 [Qwen][ROCm] Flash Attention Rotary Embeddings (#24642) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
leo-pony
422f2cca4b [Platform][CI] Added OOT platform interface e2e test that running on Ascend NPU (#25470) 
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Cyrus Leung
3884dce376 [Model] Use merge_by_field_config for MM models (D-F) (#26076) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Cyrus Leung
00c0b25e82 [Model] Use merge_by_field_config for MM models (A-C) (#26073) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucas Wilkinson
0655b90d80 [FA/Chore] Bump vllm-flash-attention (#25537) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Thomas Parnell
83fa298682 Change size of single CUDA graph for CI to 4 (#26089) 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Huy Do
5a083ce2ea Update base image to 22.04 (jammy) (#26065) 
Signed-off-by: Huy Do <huydhn@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
pwschuurman
115019045d Run:ai model streamer add GCS package support (#24909) 
Signed-off-by: Peter Schuurman <psch@google.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Nick Hill
93d2be10b6 [Misc] Make handling of SamplingParams clearer in n>1 case (#26032) 
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Gregory Shtrasberg
91e10c725c [ROCm][Bugfix] Add missing parameter to ROCm backend (#26029) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Jerry Zhang
2ae74a80af Support RL online quantization with torchao (#23014) 
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucas Wilkinson
ac1598d166 [BugFix] ChunkedLocalAttention is currently not CG compatible (#26034) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Wentao Ye
ce8ee3d9e7 [Bug] Fix Negative Cuda Memory Usage (#25683) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Hosang
d4a83e01bb [ROCm][Build] Add support for AMD Ryzen AI MAX / AI 300 Series (#25908) 
Signed-off-by: Hosang Yoon <hosang.yoon@amd.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucas Wilkinson
90529cec41 [BugFix][DP/EP] Fix CUTLASS MLA hang under load (#26026) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Michael Goin
bba7623426 [CI] Tweaks to GPT-OSS Eval (Blackwell) for stability (#26030) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Huamin Li
d2f544018f Fix test_mamba_ssm_ssd.py due to missing _query_start_loc_to_chunk_indices_offsets (#25995) 
Signed-off-by: Huamin Li <3ericli@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Johnny
ed7eb771a3 [NVIDIA] Blackwell Family (#24673) 
Signed-off-by: Johnny <johnnynuca14@gmail.com>
Signed-off-by: johnnynunez <johnnynuca14@gmail.com>
Signed-off-by: Johnny <johnnync13@gmail.com>
Signed-off-by: Salvatore Cena <cena@cenas.it>
Co-authored-by: Aidyn-A <31858918+Aidyn-A@users.noreply.github.com>
Co-authored-by: Salvatore Cena <cena@cenas.it>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Kenichi Maehashi
0944358a90 [Bugfix] Apply same sampling parameters for both n=1 and n>1 (#26005) 
Signed-off-by: Kenichi Maehashi <maehashi@preferred.jp>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Nathan Scott
aeff0604bb [Benchmark] Finish documented v0.11.0 deprecation of --endpoint-type (#26007) 
Signed-off-by: Nathan Scott <nathans@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
billishyahao
a561b9832d [MISC] Fix misleading batch_size_capture_list when cuda_graph_sizes < 4 (#25829) 
Signed-off-by: billishyahao <bill.he@amd.com>
Co-authored-by: Luka Govedic <ProExpertProg@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Harry Mellor
e8773e620f [CI] Only capture a single CUDA graph size in CI by default (#25951) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Cyrus Leung
63c56cbb25 [Misc] Factor out common _apply_feature_select_strategy (#26003) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Wenlong Wang
25e5b9ccec [BugFix][MM] Fix Nonetype error when video is cache in qwen2.5-omni-thinker (#26004) 
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
nadathurv
b9ed8c9679 [Doc] updating torch.compile doc link (#25989) 
Signed-off-by: nadathurv <work.vnadathur@gmail.com>
Signed-off-by: WorldExplored <srreyansh.sethi@gmail.com>
Co-authored-by: Srreyansh Sethi <107075589+WorldExplored@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucia Fang
9506409fc6 [Misc]allow disable pynccl (#25421) 
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Harry Mellor
fda819837e Update to Transformers v4.56.2 (#24638) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucas Wilkinson
7c795fdf41 [BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Zhewen Li
6444f65a2b [Bugfix] Fix __syncwarp on ROCM (#25996) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Roger Wang
4c094b339e [MM] Add text-only mode for Qwen3-VL (#26000) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Param
cd0bbf5de2 Fix INT8 quantization error on Blackwell GPUs (SM100+) (#25935) 
Signed-off-by: padg9912 <phone.and.desktop@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Wentao Ye
2b6b859916 [Log] Optimize Log for FP8MOE (#25709) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Salvatore Cena
04cb503fda Update launch_bounds_utils.h for correct compile on Multiple Cuda Arch - PTXAS out of range Warning (#25843) 
Signed-off-by: Salvatore Cena <cena@cenas.it>
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 13:35:57 -07:00
Lucia Fang
d437ba32fd [Model] MTP fallback to eager for DeepSeek v32 (#25982) 
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Lucas Wilkinson
e734a2a085 [Misc] Make EP kernels install script support uv (#25785) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00
Andrew Xia
fd56f2e644 [gpt-oss] use vLLM instead of openai types for streaming (#25186) 
Signed-off-by: Andrew Xia <axia@meta.com>
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-10-03 13:35:57 -07:00