xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-03-21 11:03:35 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,469 Commits 155 Branches 89 Tags
Commit Graph

12469 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
weichen
0431508388 Use request_id as the identifier when removing a request 
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
weichen
0000d981d2 add ut for sjf scheduler policy 
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Harry Mellor
da9d153112 Delete now empty file 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Harry Mellor
58615e5889 docstring 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Harry Mellor
9e8d9e1231 Consolidate SJF code and remove global variable 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Harry Mellor
53d57d9dca Remove tuple stuff 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Harry Mellor
601387735c Fix removal from heap 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
4fe722fae5 abstracting common code to HeapBasedRequestQueue 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
cc0a8ae572 naming 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Harry Mellor
ac674f6fc7 Move docstring 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
6413793466 Update scheduler.py 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
779769ea97 Create __init__.py 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
ed2a808252 Update normalized_scorer.py 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
b04f678659 linting 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
1e8b313afb linting 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
db3e0a576e linting 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
dd0e1224bc linting 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
379eabac7f linting 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
e14d347982 use heap 
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Pr0Wh1teGivee
0098c3fb93 [Feat][Sched] Add SJF Scheduling Policy 
Co-authored-by: HiC4Sh1e <chenjie137@huawei.com>
Co-authored-by: JiahongZhang-Work <iscocheung@gmail.com>
Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
 2025-12-24 16:30:26 +08:00
Roger Young
c02a2705f9
Update MiniMax-M2 ToolCall and add MiniMax-M2.1 in Docs (#31083) 
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
 2025-12-22 05:28:40 +00:00
Kevin McKay
cf8eed7bef
[Bugfix][ROCm] Fix typo: is_linear_fp8_enaled -> is_linear_fp8_enabled (#31109) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
 2025-12-21 21:14:58 -08:00
Kevin McKay
44ae85f725
[Misc] Fix typo: 'occured' -> 'occurred' (#31120) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
 2025-12-21 21:14:27 -08:00
Kevin McKay
14c3e6ade3
[Misc] Fix spelling typos in model comments (#31117) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
 2025-12-21 21:14:14 -08:00
Kevin McKay
42b42824ae
[Misc] Fix grammar errors in comments and messages (#31115) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
 2025-12-21 21:14:02 -08:00
Kevin McKay
ec58c10ce1
[Misc] Fix quantization-related typos (#31116) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
 2025-12-21 21:13:48 -08:00
Kevin McKay
8c084de59d
[Misc] Fix spelling typos in comments (#31114) 
Signed-off-by: c0de128 <kevin.mckay@outlook.com>
 2025-12-21 21:13:14 -08:00
CedricHuang
19cc9468fd
[Feature]: Support NVIDIA ModelOpt HF FP8 variants FP8_PER_CHANNEL_PER_TOKEN and FP8_PB_WO in vLLM (#30957) 2025-12-21 22:34:49 -05:00
Jee Jee Li
097978a15d
[Kernel] Enable fused_qknorm_rope_kernel supports partial rope (#30821) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-12-21 18:39:22 -08:00
Lucas Wilkinson
7e065eba59
[CI] Fix "2 Node Tests (4 GPUs in total)" (#31090) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-22 10:32:40 +08:00
Steve Westerhouse
9d701e90d8
[Doc] Clarify FP8 KV cache computation workflow (#31071) 
Signed-off-by: westers <steve.westerhouse@origami-analytics.com>
 2025-12-22 08:41:37 +08:00
Michael Goin
06d490282f
[NVFP4][Perf] Tune NVFP4 input quant kernel for small batch size (#30897) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-21 09:41:57 -08:00
Robert Shaw
b471092d3a
[MoE Refactor][4/N] Marlin Fp8 Mk (#31036) 2025-12-21 12:37:42 -05:00
Ameen Patel
93cabc417c
ci: add nvidia-smi warmup before Prime-RL integration test (#31093) 
Signed-off-by: AmeenP <ameenp360@gmail.com>
 2025-12-21 15:43:01 +00:00
Chauncey
bb80f69bc9
add aarnphm and chaunceyjiang to the new tool_parser directory (#31088) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2025-12-21 03:24:34 +00:00
汪志鹏
3e92b2b7ac
[BugFix]fix gpt-oss v1/completions response bug (#30608) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: bbrowning <bbrownin@redhat.com>
 2025-12-21 10:39:31 +08:00
Jinzhen Lin
7c73ceb581
[Quantization] add marlin w4a8/w8a8 check (#31061) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
 2025-12-20 21:58:11 +00:00
Lucas Wilkinson
ae0770fa6b
[CI] Fix H200 Distributed test (#31054) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-20 16:48:49 -05:00
Jinzhen Lin
ee52d9901d
[Quantization] support logical_widths for fp8 marlin (#30962) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-20 12:02:57 -08:00
baonudesifeizhai
54c8924384
[MoE Refactor][5/N] Isolate zero expert to LongCatFlash (#28891) 
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: Dongjie Zou <85092850+baonudesifeizhai@users.noreply.github.com>
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robertgshaw2@gmail.com>
 2025-12-20 18:22:04 +00:00
Yan Ma
560ae9638c
[XPU] enable fp8 online streaming quantization (#30944) 
Signed-off-by: Yan Ma <yan.ma@intel.com>
 2025-12-20 13:45:27 +00:00
Jeffrey Wang
1501a4070e
[Bugfix] Read truncate_prompt_tokens from pooling_params in AsyncLLM.encode() (#31013) 
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
 2025-12-20 10:29:31 +00:00
Lucas Wilkinson
ff2168bca3
[CI] FIx fixture 'siglip_attention_config' not found (#31053) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-20 03:46:15 +00:00
Gregory Shtrasberg
0be149524c
[ROCm][CI/Build] Update ROCm dockerfiles (#30991) 
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
 2025-12-20 03:19:12 +00:00
zejunchen-zejun
d52c5096d7
[Bugfix] fix the alias bug of AttentionBackendEnum when register CUSTOM attention backend to vllm (#30869) 
Signed-off-by: zejunchen-zejun <zejun.chen@amd.com>
 2025-12-20 09:03:35 +08:00
Yuxuan Zhang
8a7a414374
GLM-4.7 Tool Parser and Doc Update (#30876) 
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
 2025-12-20 00:09:58 +00:00
Robert Shaw
95befecc18
[MoE Refactor][2/N] Use Modular Kernels for Fp8 (#30825) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-12-19 23:36:38 +00:00
Wentao Ye
4cf9429897
[Bug] Fix error 'Dynamo failed to run FX node with fake tensors for Deepseek V3.2 (#31046) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-19 23:31:31 +00:00
Robert Shaw
83a317f650
[MoE Refactor][3/N] Deprecate cutlass block quant fp8 (b200) (#30990) 
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
 2025-12-19 13:09:54 -08:00
Lucas Wilkinson
5f6477d1d0
[BugFix] Fix TypeError: unhashable type: 'dict' when serving deepseek32 (#30924) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-19 16:07:54 -05:00