10031 Commits

Author SHA1 Message Date
Fanli Lin
2ab27b70f5 [XPU] Fix MOE DP accuracy issue on XPU (#25465)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Peter Pan
a500f7cc09 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Chauncey
1b75f784b8 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Joel
0eddd2b528 [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>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Isotr0py
030774abcf [CI/Build] Fix disabled v1 attention backend selection test (#25471)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
vllmellm
77389d87b2 [docs] Benchmark Serving Incorrect Arg (#25474)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Jee Jee Li
59659b74c4 [Core] Optimize LoRA weight loading (#25403)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Isotr0py
3b96eafdb0 [Bugfix] Fix idefics3 tie_word_embeddings (#25454)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Andreas Hartel
fb64e67533 [Test]: Hermes tool parser stream output error in Qwen3 case (#25203)
Signed-off-by: Andreas Hartel <andreas.hartel@aleph-alpha.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Cyrus Leung
215da8510d [Misc] Move DP for ViT code inside model executor dir (#25459)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Zhikaiiii
c4a15ee240 [Frontend] Add a new xml-based tool parser for qwen3-coder (#25028)
Signed-off-by: Zhikaiiii <1658973216@qq.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Ming Yang
3a640b8f74 Handle triton kernel import exception (#25319)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Cyrus Leung
0a1397c7df [Model] Enable DP for ViT in Qwen2-VL (#25445)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Chendi.Xue
921945c81e [NIXL][OOT platform] support nixl_connector with oot platform and other nixl_backend (#25121)
Signed-off-by: Chendi Xue <Chendi.Xue@intel.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Varun Sundar Rabindranath
675fc471bf [DP/EP][GPTOSS] Use triton matmul-ogs kernels for GPTOSS DP/EP (#24588)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Michael Yao
b0ae0ad935 [Docs] Fix griffe warnings in vllm/lora/ops (#25369)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Michael Goin
e99b286f01 [Bugfix] Remove contiguous output req for context parallel MLA (#25414)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Lucia Fang
23a7805022 [benchmarks]allow skip ready check for bench serve (#25420)
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Kunshang Ji
e3a3c738b0 [XPU] Fix compile_size is None case. (#25433)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
JJJYmmm
e41946ecdb [feat] Support MRoPE + YaRN (#25384)
Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Wentao Ye
f071a31ede [Bug] Fix Long Context OOM Issue (#25290)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Isotr0py
1b30043f0d [V0 deprecation] Remove _set_default_args_v0 function (#25409)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Isotr0py
a0b5617263 [V0 deprecation] Remove platform v1 controling interface (#25410)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Wentao Ye
e6c22d2b2f [Perf] Apply torch.compile for per_block_cast_to_fp8 (#24611)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Alexander Matveev
dbb029cfe1 [Performance] Remove input pads in cutlass_mla and optimize v_proj output handling (#25184)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Matthew Bonanni
25dd155e60 [BugFix] [DP/EP] Fix slow execution when BS <= DP (#25407)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Chris Bamford <chrisbam4d@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Nicolò Lucchesi
864bbe36f0 [Bugfix] Fix missing clear_connector_metadata (#25397)
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Russell Bryant
e97cf2e32b [Core] Drop overly aggressive whisper assertion (#25408)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Luka Govedič
d96a3fc653 [Bugfix] fix custom op test (#25429)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:54 -07:00
Alec S
aac85cc6d6 [Frontend] Responses API MCP tools for built in tools and to pass through headers (#24628)
Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Alec S <10566873+alecsolder@users.noreply.github.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Johnny Yang
f1e3d031e4 [TPU] update torch_xla dependency for PyPI compatibility (#25278)
Signed-off-by: Johnny Yang <johnnyyang@google.com>
Co-authored-by: Chengji Yao <chengjiyao@google.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Cyrus Leung
6e9229e919 [CI/Build] Skip Qwen3-VL initialization tests until models are actually released (#25394)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Or Ozeri
ff54b6bfe3 [KV offload][5/N] Add CPUOffloadingSpec (#24251)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Luka Govedič
6dbbecd5b2 [torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: luka <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Simon Mo
6850bfe15c [misc] Remove RFC review hours reference (#25416)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Lucia Fang
d988b84e8e [DP] support torchrun external launcher with Data Parallelism (#24899)
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Michael Goin
7337ec6c9f [CI Failure] Fix fp8 kv cache on <SM90 (#25396)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
ElizaWszola
90ba32a0bf [Compiler] Disable Inductor standalone compile by default (#25391)
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Daisy-Ma-coder
2a8bd2b93b [CLI env var] Add VLLM_FLASH_ATTN_MAX_NUM_SPLITS_FOR_CUDA_GRAPH in env variables (#25274)
Signed-off-by: qqma <qqma@amazon.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: qqma <qqma@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Bowen Wang
3968ae72ed [EPLB] Reduce EPLB Inference Overhead (#24573)
Signed-off-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Burkhard Ringlein
e55ffe3595 [V1][Attention] Split triton_attn in triton-only and rocm specific backends (#24648)
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Csrayz
4057e2b162 [Bugfix] Fix several issues with p2p xPyD in GET type (#23993)
Signed-off-by: Csrayz <jover@cmbchina.com>
Signed-off-by: ivyilike <pww123@cmbchina.com>
Co-authored-by: ivyilike <pww123@cmbchina.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Sara-KS
cc494282a9 [Kernel] MI-300X triton moe configs (#23445)
Signed-off-by: Sara Kokkila Schumacher <saraks@ibm.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Harry Mellor
44be2b7349 Make mypy behave like a proper pre-commit hook (#25313)
Signed-off-by: Harry Mellor <19981378+hmellor@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 13:35:53 -07:00
Harry Mellor
104e62fbc8 Make pickle import check fast (#25379)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Cyrus Leung
ddf4e1f56f [Misc] Remove unused encoder-decoder error strings (#25374)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Yizhou
cbba9bd0b0 refactor: abstract graph mode support into platform interface (#25161)
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Nicolò Lucchesi
4bc6b5d2c3 [TPU] Deprecate xm.mark_step in favor of `torch_xla.sync (#25254)
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Nicolò Lucchesi
8d8de42790 [TPU][Bugfix][CI] Fix broken tests/build dependency (#25255)
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00
Eldar Kurtić
ef85a438da Enable Eagle3 speculative decoding for GPT-OSS model (#25246)
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-10-03 13:35:53 -07:00