5517 Commits

Author SHA1 Message Date
Charlie Fu
e85829450d
[Feature][ROCm]Enable fusion pass for torch.compile on ROCm (#15050)
Signed-off-by: charlifu <charlifu@amd.com>
2025-03-31 04:42:18 -07:00
Jennifer Zhao
effc5d24fa
[Benchmark] Update Vision Arena Dataset and HuggingFaceDataset Setup (#15748)
Signed-off-by: Jennifer Zhao <ai.jenniferzhao@gmail.com>
2025-03-31 15:38:58 +08:00
Chengyang LIU
18ed3132d2
[Misc] update the comments (#15780)
Signed-off-by: chengyang liu <lcy4869@gmail.com>
Co-authored-by: chengyang liu <lcy4869@gmail.com>
2025-03-30 19:39:56 -07:00
Woosuk Kwon
9b459eca88
[V1][Scheduler] Avoid calling _try_schedule_encoder_inputs for every request (#15778)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-30 14:10:42 -07:00
yihong
70fedd0f79
fix: Comments to English for better dev experience (#15768)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-30 10:47:57 -07:00
kYLe
bb103b29bf
[Bugfix] Added embed_is_patch mask for fuyu model (#15731)
Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
2025-03-30 03:45:08 -07:00
yihong
248e76c4df
fix: lint fix a ruff checkout syntax error (#15767)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-03-30 03:36:02 -07:00
Cyrus Leung
803d5c35f3
[V1] Override mm_counts for dummy data creation (#15703)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-30 03:20:42 -07:00
pansicheng
7fd8c0f85c
fix test_phi3v (#15321)
Signed-off-by: pansicheng <sicheng.pan.chn@gmail.com>
2025-03-30 02:01:34 -07:00
Reid
44c3a5abc3
[doc] update conda to usage link in installation (#15761)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
2025-03-30 08:12:13 +00:00
Julien Denize
6909a76201
[Bugfix] Fix Mistral guided generation using xgrammar (#15704)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
2025-03-29 20:20:19 -07:00
Chauncey
045533716b
[CI] xgrammar structured output supports Enum. (#15757)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-03-29 20:20:02 -07:00
Isotr0py
3c0ff914ac
[Bugfix] Fix Mllama interleaved images input support (#15564)
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
2025-03-29 18:11:15 +00:00
Woosuk Kwon
2bc4be4e32
[V1][Minor] Simplify rejection sampler's parse_output (#15741)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-29 09:25:17 -07:00
Roger Wang
c67abd614f
[V1] Support interleaved modality items (#15605)
Signed-off-by: Roger Wang <ywang@roblox.com>
2025-03-29 06:30:09 -07:00
shangmingc
6fa7cd3dbc
[Feature][Disaggregated] Support XpYd disaggregated prefill with MooncakeStore (#12957)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-03-29 04:01:46 -07:00
wwl2755
94744ba41a
[V1] [Feature] Collective RPC (#15444)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
2025-03-29 03:39:14 -07:00
TJian
4965ec42d2
[FEAT] [ROCm] Add AITER int8 scaled gemm kernel (#15433)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-03-29 03:33:56 -07:00
Reid
73aa7041bf
[doc] update doc (#15740)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
2025-03-29 04:27:22 +00:00
yarongmu-google
7c1f760024
[Kernel][TPU][ragged-paged-attn] vLLM code change for PR#8896 (#15659)
Signed-off-by: Yarong Mu <ymu@google.com>
2025-03-28 21:13:15 -07:00
Nicolò Lucchesi
da461f3cbf
[TPU][V1][Bugfix] Fix w8a8 recompiilation with GSM8K (#15714)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-03-28 21:13:06 -07:00
Jinzhen Lin
5b800f0932
[Bugfix] set VLLM_WORKER_MULTIPROC_METHOD=spawn for vllm.entrypoionts.openai.api_server (#15700)
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
2025-03-28 21:12:26 -07:00
cyyever
8427f70493
Use numba 0.61 for python 3.10+ to support numpy>=2 (#15692)
Signed-off-by: cyy <cyyever@outlook.com>
2025-03-29 12:11:51 +08:00
Russell Bryant
7a7992085b
[CI] Speed up V1 structured output tests (#15718)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-03-28 21:10:45 -07:00
Varun Sundar Rabindranath
1286211f57
[Bugfix] LoRA V1: add and fix entrypoints tests (#15715)
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
2025-03-28 21:10:41 -07:00
Nick Hill
6d531ad7b8
[Misc][V1] Misc code streamlining (#15723)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-03-28 20:59:47 -07:00
Ce Gao
762b424a52
[Docs] Document v0 engine support in reasoning outputs (#15739)
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
2025-03-29 03:46:57 +00:00
pengyuange
de1cb38769
[Model] Support Skywork-R1V (#15397)
Signed-off-by: jiacai.liu <932997367@qq.com>
Co-authored-by: jiacai.liu <932997367@qq.com>
2025-03-28 20:39:21 -07:00
Gregory Shtrasberg
c802f5430d
[ROCm][AMD][Build] Update AMD supported arch list (#15632)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-03-28 20:39:18 -07:00
simpx
cff8991a50
[Docs][V1] Optimize diagrams in prefix caching design (#15716) 2025-03-29 03:33:58 +00:00
daniel-salib
f3f8d8fff4
implement prometheus fast-api-instrumentor for http service metrics (#15657) 2025-03-29 00:12:02 +00:00
Reid
26df46ee59
[Misc] cli auto show default value (#15582)
Signed-off-by: reidliu41 <reid201711@gmail.com>
2025-03-28 22:23:00 +00:00
Alexander Matveev
c3f687ac22
[V1] TPU - Fix the chunked prompt bug (#15713)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
2025-03-28 20:19:04 +00:00
Luka Govedič
04437e313d
[Bugfix] [torch.compile] Add Dynamo metrics context during compilation (#15639)
Signed-off-by: luka <luka@neuralmagic.com>
2025-03-28 14:01:09 -06:00
Robert Shaw
038bededba
[TPU] [Perf] Improve Memory Usage Estimation (#15671)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2025-03-28 17:37:52 +00:00
shangmingc
d03308be0c
[Misc] Remove stale func in KVTransferConfig (#14746)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-03-28 17:33:32 +00:00
Cyrus Leung
c6bc0034d0
[Misc] Remove unused utils and clean up imports (#15708)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-28 09:41:16 -07:00
Woosuk Kwon
70e132244a
[Minor] Remove TGI launching script (#15646)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-03-28 09:30:08 -07:00
Michael Goin
47e9038d23
Fix cpu offload testing for gptq/awq/ct (#15648)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-03-29 00:29:32 +08:00
Kebe
432cf22a6a
[Bugfix] Fix regex compile display format (#15368)
Signed-off-by: Kebe <mail@kebe7jun.com>
2025-03-28 08:58:44 -07:00
Reid
2914006fe0
[doc] add missing imports (#15699)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
2025-03-28 15:56:48 +00:00
Russell Bryant
7329ff5468
[V1] Support disable_any_whtespace for guidance backend (#15584)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-03-28 23:46:45 +08:00
Cyrus Leung
541d1df486
[Bugfix] embed_is_patch for Idefics3 (#15696)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-28 08:27:52 -07:00
Chauncey
3b00ff9138
[Bugfix][v1] xgrammar structured output supports Enum. (#15594)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-03-28 06:14:53 -07:00
Jee Jee Li
91276c5721
[Model] Adding torch compile annotations to chatglm (#15624)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-28 21:14:09 +08:00
Harry Mellor
0b4167526d
[Docs] Add "Generation quality changed" section to troubleshooting (#15701)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-03-28 13:03:21 +00:00
Reid
fd5fd26902
[Frontend] update priority for --api-key and VLLM_API_KEY (#15588)
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
2025-03-28 19:40:12 +08:00
Ce Gao
3bbaacbe15
[Bugfix][Frontend] Eliminate regex based check in reasoning full generator (#14821)
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
2025-03-28 11:20:35 +00:00
Lize Cai
a10314c6b3
[Misc] Fix test_sleep to use query parameters (#14373)
Signed-off-by: Lize Cai <lize.cai@sap.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-03-28 18:00:14 +08:00
Jee Jee Li
70f2c2a709
[Bugfix] Fix 'InductorAdaptor object has no attribute 'cache_dir' (#15674)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-03-28 17:10:40 +08:00