biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
10,584 Commits 2 Branches 140 Tags
168e578efc3f9fb1beaf1e89809d5678ed375bdb
Commit Graph

199 Commits

Author SHA1 Message Date
Isotr0py
6ac5e06f7c [Chore] Clean up pytorch helper functions in vllm.utils (#26908) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: isotr0py <2037008807@qq.com>
 2025-10-18 09:48:22 -07:00
iAmir97
1d165d6d85 [Chore] Separate out vllm.utils.mem_utils (#27143) 
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-18 10:06:59 +00:00
Hanchenli
7c572544e4 [GPT-OSS] Structure_Tag support for gpt-oss tool-call in cot (#25515) 
Signed-off-by: Hanchenli <lihanc2002@gmail.com>
Signed-off-by: Hanchenli <61769611+Hanchenli@users.noreply.github.com>
Signed-off-by: Wei Wei <wwei6@meta.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Wei Wei <wwei6@meta.com>
Co-authored-by: Wei Wei <weiweinpu@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
 2025-10-17 21:55:54 -07:00
Michael Goin
950cf9e58e [Bugfix] Use PIECEWISE cudagraphs on Blackwell if max_model_len > 131072 (#27114) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-10-17 19:47:18 +00:00
Harry Mellor
6c9fdbf725 [Docs] Replace rst style double-backtick with md single-backtick (#27091) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-17 02:47:34 -07:00
Cyrus Leung
4d4d6bad19 [Chore] Separate out vllm.utils.importlib (#27022) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-17 00:48:59 +00:00
Harry Mellor
fb5e10d3fb Refactor Transformers backend to use mixins (#26906) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-16 21:50:39 +00:00
Bram Wasti
b2f78cbad4 [small][batch invariance] Rename the env and internal flags to simplify usage (#26855) 
Signed-off-by: Bram Wasti <bwasti@meta.com>
 2025-10-16 21:40:25 +00:00
Mandy Li
ac3ed5a815 Support block size of 256 used by Intel HPU (#26883) 
Signed-off-by: mandy-li <mandy.j.li@intel.com>
 2025-10-16 15:10:57 -04:00
Bram Wasti
7d8975de84 Deepseek-v3 Batch Invariant on 8xH100 (#26609) 
Signed-off-by: Bram Wasti <bwasti@meta.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-10-15 22:06:02 -07:00
ahao-anyscale
582f2c6be7 [BUG] Allow runai_streamer_sharded in config check (#26958) 
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
 2025-10-15 20:05:14 -07:00
Sam/Samuel
14f8456344 [Feature]: Use pydantic validation in observability.py config (#26637) 
Signed-off-by: Samuel Wu <cernunnos1710@gmail.com>
Signed-off-by: Sam/Samuel <57896620+cern1710@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-15 16:44:03 +00:00
wangxiyuan
8f4b313c37 [Misc] rename torch_dtype to dtype (#26695) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-10-15 12:11:48 +00:00
wangxiyuan
db1764e4e0 [Platform] allow platform to init dp group (#22243) 
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
 2025-10-15 02:32:17 -07:00
Morrison Turnansky
96b9aa5aa0 [Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change compilation level to compilation mode, deprecation compilation level (#26355) 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-10-15 02:51:16 +00:00
Luka Govedič
2dcd12d357 [torch.compile] Fix tests for torch==2.9 inductor partition (#26116) 
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
 2025-10-14 19:55:02 -04:00
Boyuan Feng
ca683a2a72 use combo kernel to fuse qk-norm and qk-rope (#26682) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-10-14 09:40:59 -04:00
Jaya Yuan
ea97940d6c [DCP] Support Decode Context Parallel (DCP) for GQA with FlashAttention (#24864) 
Signed-off-by: yuanyongjie.yyj <yuanyongjie.yyj@antgroup.com>
Signed-off-by: FENP <32334296+FENP@users.noreply.github.com>
Signed-off-by: Jaya Yuan <yuanyongjie.yyj@antgroup.com>
 2025-10-14 13:07:50 +00:00
Vladislav Bronzov
c715ba3735 [Feature] Change vllm.py with pydantic validation (#26726) 
Signed-off-by: Vladislav <vladislav.bronzov@gmail.com>
Signed-off-by: Vladislav Bronzov <58587565+VladOS95-cyber@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-14 12:00:54 +00:00
Cyrus Leung
9c4cb68339 [Chore] Remove SupportsV0Only interface and update supported models docs (#26783) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-10-14 04:55:10 -07:00
Chendi.Xue
7e6edb1469 [NIXL][HeteroTP] Enable KV transfer from HND prefill to NHD decode (#26556) 
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
 2025-10-14 09:46:05 +00:00
Ryan Li
481545b397 scheduler.py: Update the name of the default scheduler. (#26758) 
Signed-off-by: Ryan Li <ryanli@ryanli.org>
 2025-10-14 06:52:21 +00:00
Michael Goin
3e051bda82 [UX] Replace VLLM_ALL2ALL_BACKEND with --all2all-backend (#26732) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-10-13 18:12:52 -07:00
Morrison Turnansky
e3fdb627d9 [FrontEnd] UNREVERT CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops (#26502) 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@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: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2025-10-13 22:47:16 +00:00
Wentao Ye
314285d4f2 [CI] Fix mypy for vllm/distributed (#26593) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-13 16:02:24 -04:00
Anand Roy
10214b6935 [FEATURE]: Use pydantic validation in multimodal.py config (#26629) 
Signed-off-by: Anand Roy <86306690+andycandy@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-13 07:56:59 -07:00
wang.yuqi
767c3ab869 [Model][0/N] Improve all pooling task | clean up (#25817) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-10-13 16:44:50 +08:00
Harry Mellor
8fcaaf6a16 Update Optional[x] -> x | None and Union[x, y] to x | y (#26633) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-12 09:51:31 -07:00
Jaya Yuan
b91d8db873 [Bugfix][DCP] Set default CUDAGraphMode to PIECEWISE for DCP (#26574) 
Signed-off-by: FENP <32334296+FENP@users.noreply.github.com>
 2025-10-12 09:58:38 +00:00
wang.yuqi
76852017ea [MISC] Rename the torch profiler filename as instance_id+rank_id for merging the Profiler results of each Rank (#25867) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-10-12 09:29:08 +00:00
Angela Yi
01653a917b [compile] Fix inductor partition config (#26645) 
Signed-off-by: angelayi <yiangela7@gmail.com>
 2025-10-11 21:03:14 +00:00
baonudesifeizhai
cddce79fda [torch.compile] Make inductor partition rules respect splitting_ops #25691 (#25845) 
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-10-10 16:35:28 +00:00
Ashwin Phadke
ab196edefb Remove LoRA bias support (#25807) 
Signed-off-by: Ashwin Phadke <ashwinphadke12@rediffmail.com>
Signed-off-by: Ashwin Phadke <23502062+ashwin-phadke@users.noreply.github.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-10-10 09:50:33 +00:00
Lucas Wilkinson
29255cfc3b [Spec-Decode] Support piecewise cudagraphs for Eagle head (#25109) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
 2025-10-10 01:20:31 -04:00
Harry Mellor
e246ad6f0c Upgrade Pydantic to v2.12.0 and remove hack for Python 3.13 (#26481) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-09 06:02:40 -07:00
Jiangyun Zhu
5728da11ea Revert #26113 "[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops" (#26472) 
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
 2025-10-09 05:43:55 -07:00
Simon Danielsson
92be3f3517 [Feature] Use pydantic validation in parallel.py config (#26417) 
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-09 12:41:31 +00:00
Simon Danielsson
e4791438ed [Feature] Use pydantic validation in lora.py and load.py configs (#26413) 
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
 2025-10-09 02:38:33 -07:00
Jee Jee Li
1b2c440cd6 [Core] Relax the LoRA max rank (#26461) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-10-08 23:47:14 -07:00
Naveenraj Kamalakannan
e614ab7806 Separate MLAAttention class from Attention (#25103) 
Signed-off-by: Naveenraj Kamalakannan <therealnaveenkamal@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
 2025-10-08 17:11:11 -07:00
Morrison Turnansky
e1ba235668 [BugFix] Fix failing test quantization/test_compressed_tensors.py::test_compressed_tensors_fp8_block_enabled (#26436) 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
 2025-10-08 20:04:12 +00:00
Vinay R Damodaran
b25d7b5657 [Feature] Change cache.py with pydantic validation (#26390) 
Signed-off-by: Vinay Damodaran <vrdn@hey.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-08 11:12:59 -07:00
Harry Mellor
e09d1753ec Remove Python 3.9 support ahead of PyTorch 2.9 in v0.11.1 (#26416) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-08 10:40:42 -07:00
Harry Mellor
2f99f2f506 Tidy vllm/config/__init__.py to only add classes and functions (#26405) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-08 07:10:00 -07:00
Ayush Satyam
5e65d6b2ad fix[DP][v1]: Prevent hangs from mismatched worker configurations (#26218) 
Signed-off-by: Ayush Satyam <ayushsatyam146@gmail.com>
 2025-10-07 22:55:08 -07:00
liangel-02
b32260ab85 [torchao] safetensors integration (#25969) 
Signed-off-by: Angel Li <liangel@meta.com>
 2025-10-07 20:12:35 -06:00
Morrison Turnansky
0c824fc46f [Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops (#26113) 
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@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: Jiangyun Zhu <riverclouds.zhu@qq.com>
 2025-10-07 12:53:43 -07:00
Grant Holmes (Ren)
d100d78eb3 Optimize KV cache distribution for asymmetric pipeline parallelism (#25164) 
Signed-off-by: gholmes829 <g.holmes429@gmail.com>
 2025-10-07 09:20:30 +00:00
Michael Goin
c6873c4e6d [UX] Support nested dicts in hf_overrides (#25727) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-10-07 11:19:16 +08:00
Sage Moore
2111b4643c [Core] Simplify the Dp padding/should ubatch coordination logic (#25768) 
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-10-07 01:57:49 +00:00