3754 Commits

Author SHA1 Message Date
LiuXiaoxuanPKU
b484b79504 fix 2025-04-01 15:46:41 -07:00
LiuXiaoxuanPKU
8fcd4d18e0 minor 2025-04-01 13:51:04 -07:00
LiuXiaoxuanPKU
50e2788383 dsd draft 2025-04-01 13:33:07 -07:00
shangmingc
239b7befdd
[V1][Spec Decode] Remove deprecated spec decode config params (#15466)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-03-31 09:19:35 -07:00
Cyrus Leung
09e974d483
[Bugfix] Check dimensions of multimodal embeddings in V1 (#15816)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-31 09:01:35 -07:00
Mrm
037bcd942c
[Bugfix] Fix missing return value in load_weights method of adapters.py (#15542)
Signed-off-by: noc-turne <2270929247@qq.com>
2025-03-31 06:56:42 -07:00
Alex Brooks
c2e7507ad4
[Bugfix] Fix Crashing When Loading Modules With Batchnorm Stats (#15813)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2025-03-31 13:23:53 +00:00
Naveassaf
3aa2b6a637
[Model] Update support for NemotronNAS models (#15008)
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
2025-03-31 20:35:14 +08:00
youkaichao
555aa21905
[V1] Fully Transparent Implementation of CPU Offloading (#15354)
Signed-off-by: youkaichao <youkaichao@gmail.com>
2025-03-31 20:22:34 +08:00
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
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
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
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
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
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
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
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
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
Kebe
432cf22a6a
[Bugfix] Fix regex compile display format (#15368)
Signed-off-by: Kebe <mail@kebe7jun.com>
2025-03-28 08:58:44 -07:00
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
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
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
Ce Gao
32b14baf8a
[Refactor][Frontend] Keep all logic about reasoning into one class (#14428)
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
2025-03-28 00:23:30 -07:00
Cyrus Leung
355f66348c
[V1] Remove legacy input registry (#15673)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-27 23:34:34 -07:00
Cyrus Leung
8693e47e6a
[Bugfix] Fix mm_hashes forgetting to be passed (#15668)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-03-28 05:51:05 +00:00
Jason (Siyu) Zhu
cec8c7d7f8
Refactor error handling for multiple exceptions in preprocessing (#15650)
Signed-off-by: JasonZhu1313 <jasonchu13@outlook.com>
2025-03-28 03:27:20 +00:00
Gregory Shtrasberg
4d0ec37267
[Quantization][FP8] Adding support for fp8 gemm layer input in fp8 (#14578)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2025-03-28 02:58:16 +00:00
Wes
4ae17bf1e2
Revert "Use Cache Hinting for fused_moe kernel (#15511)" (#15645)
Signed-off-by: Wes Medford <wryanmedford@gmail.com>
2025-03-27 19:45:55 -07:00