Commit Graph

13302 Commits

Author SHA1 Message Date
danisereb
f999539869 Add missing import of fused_topk to benchmark_moe (#32784)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
2026-01-21 18:30:10 +00:00
Woosuk Kwon
e1da249c93 [Model Runner V2] Minor refactor for compute_slot_mappings (#32794)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2026-01-21 10:24:35 -08:00
Nick Hill
9b693d023c [Misc] Omit "disable NCCL for DP sync" startup log when not applicable (#32707)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-01-21 17:03:39 +00:00
elvischenv
808d6fd7b9 Bump Flashinfer to v0.6.1 (#30993)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
2026-01-21 08:49:50 -08:00
whx
1861ae8aae [PluggableLayer][1/N] Define PluggableLayer (Fix ci) (#32744)
Signed-off-by: whx-sjtu <2952154980@qq.com>
2026-01-21 11:38:04 -05:00
Robert Shaw
4e31b7f228 [Quantization][Deprecation] Remove RTN (#32697)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2026-01-21 16:34:42 +00:00
Pleaplusone
6c20e89c02 [ROCm][Deepseekv3.2] Refactor Sparse Indexer as CustomOp (#29287)
Signed-off-by: ganyi <ygan@amd.com>
2026-01-21 23:16:30 +08:00
Robert Shaw
85f55c943c [Quantization][Deprecation] Deprecate HQQ (#32681)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2026-01-21 09:32:40 -05:00
Robert Shaw
cea3c754c4 [Quantization][Deprecation] Remove DeepSpeedFp8 (#32679)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2026-01-21 09:32:12 -05:00
Robert Shaw
42135d6898 [MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority (#32414) 2026-01-21 08:22:33 -05:00
Divakar Verma
e14467be43 [bugfix] Aria model (#32727)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2026-01-21 05:11:31 -08:00
Kim Hee Su
7727ce35c2 [Model] Add Eagle2.5-8B Vision-Language Model support (#32456)
Signed-off-by: kimheesu <wlskaka4@gmail.com>
2026-01-21 09:39:53 +00:00
Yanwen Lin
6bb2bc71e2 [Bugfix] Force using spawn multiprocess method when it's the WSL platform (#32749)
Signed-off-by: Yanwen Lin <lyw1124278064@gmail.com>
2026-01-21 09:35:55 +00:00
Lucas Kabela
c80f92c14d [Documentation] Fix typo in docs/design/torch_compile_multimodal.md (#32741)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
2026-01-20 23:54:20 -08:00
RickyChen / 陳昭儒
f23fb5a7c1 [Bugfix] Support HF sharded weights for Mistral3/Pixtral models (#32673)
Signed-off-by: ricky-chaoju <ricky.chen@infinirc.com>
Signed-off-by: vllm-dev <ricky.chen@infinirc.com>
2026-01-20 23:27:30 -08:00
Paco Xu
360aa93f8f [Docs] Fix GitHub handle in governance process (#32582)
Signed-off-by: Paco Xu <paco.xu@daocloud.io>
2026-01-21 07:07:50 +00:00
Netanel Haber
27ca95b3c9 [Bugfix] Fix Nemotron-Nano-v2-vlm static resolution (#32682)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
2026-01-21 06:28:21 +00:00
Lucas Wilkinson
b4f64e5b02 Update FlashMLA (#32491)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-01-21 13:03:37 +08:00
shanjiaz
7ab80a8e37 Added qwen3 vision language moe support for speculative decoding (#32048)
Signed-off-by: shanjiaz <zsjwpianpian@gmail.com>
Signed-off-by: shanjiaz <43143795+shanjiaz@users.noreply.github.com>
2026-01-21 03:24:05 +00:00
gopalsarda
0900cedb3f Enable Eagle3 speculative decoding for Pixtral (LlavaForConditionalGeneration) (#32542)
Signed-off-by: gopalsarda <gopal.sarda@servicenow.com>
2026-01-21 11:18:05 +08:00
Nick Hill
6f067b1fb7 [Cleanup] Remove unused KVConnectorModelRunnerMixin methods (#32077)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-01-21 11:16:37 +08:00
Alex Brooks
27b81e010d [Bugfix] Fix Granite Vision / Don't use Siglip Pooling Head Nested Models by Default (#32299)
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
2026-01-21 11:11:52 +08:00
Or Ozeri
7013e9ac8f OffloadingConnector: Prevent redundant loads (#29087)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2026-01-21 01:15:42 +00:00
Robert Shaw
c78ee240b3 Revert "[PluggableLayer][1/N] Define PluggableLayer" (#32725) 2026-01-21 00:21:06 +00:00
Vasiliy Kuznetsov
d2389c1262 fp8 online quant: split out Fp8OnlineLinearMethod (#32189) 2026-01-20 18:13:22 -05:00
Micah Williamson
22375f8d13 [ROCm][CI] Remove DS async eplb accuracy test from AMD CI (#32717)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
2026-01-20 13:40:48 -08:00
TJian
9b67338b78 [Bugfix] Suppress log on non-ROCm platform (#32703)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2026-01-20 13:38:20 -08:00
Lucas Wilkinson
2261340806 [Misc] Remove pad_for_cudagraphs from config (#30143)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
2026-01-20 15:05:48 -05:00
Shinichi Hemmi
86c69dc54c [Bugfix] Fix byte fallback handling when using outlines (#31391)
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Co-authored-by: Kenichi Maehashi <maehashi@preferred.jp>
2026-01-20 19:48:08 +00:00
dolpm
7c5dedc247 [AOT compilation] support torch.compile inductor artifacts in VllmCompiledFunction (#25205)
Signed-off-by: dolpm <34420038+dolpm@users.noreply.github.com>
2026-01-20 19:45:59 +00:00
Cyrus Leung
193069d129 [5/N] Initialize MM components in context managers (Q-Z) (#32695)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 19:10:23 +00:00
Rahul Tuli
f0feb1cf81 Test: added acceptance length tests (#32030)
Signed-off-by: rahul-tuli <rtuli@redhat.com>
2026-01-20 18:55:15 +00:00
Cyrus Leung
09194b90a5 [Doc] Update docs for MM model development with context usage (#32691)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 10:37:35 -08:00
Woosuk Kwon
9ab4388cd3 [Model Runner V2] Support FLASHINFER_MLA backend (#32709)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2026-01-20 10:26:17 -08:00
JJJYmmm
04a9e064db [Bugfix] fix the ima issue of qwen-vit (#32687)
Signed-off-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
2026-01-20 17:21:25 +00:00
TJian
c025263ddd [Doc] [ROCm] Update ROCm getting started doc (#32580)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 09:20:08 -08:00
Wentao Ye
6c97b9b9b6 [Perf] Only clone when needed for moe_permute (#32273)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-01-20 11:34:39 -05:00
whx
4ca62a0dbd [PluggableLayer][1/N] Define PluggableLayer (#32331)
Signed-off-by: whx-sjtu <2952154980@qq.com>
2026-01-20 16:19:21 +00:00
linhaifeng
7901109ea5 [Bugfix] Fix Off-by-one error in _num_tokens_to_min_blocks calculation (#32603)
Signed-off-by: linhaifeng <1371675203@qq.com>
2026-01-20 11:13:39 -05:00
YiSheng5
13f6630a9e [XPU]Support AgRsAll2AllManager on XPU device (#32654)
Signed-off-by: yisheng <yi.sheng@intel.com>
2026-01-20 14:27:24 +00:00
Cyrus Leung
fda3f03eb2 [4/N] Initialize MM components in context managers (M-P) (#32663)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 14:06:32 +00:00
杨朱 · Kiki
bb9172030e [Metrics] Complete removal of deprecated vllm:time_per_output_token_seconds metric (#32661)
This PR completes the removal of the deprecated vllm:time_per_output_token_seconds
metric that was deprecated in v0.11, hidden in v0.12, scheduled for removal in v0.13,
but delayed until v0.15.

Signed-off-by: carlory <baofa.fan@daocloud.io>
Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com>
2026-01-20 12:28:41 +00:00
Chauncey
c4e5bdf61b [Bugfix] Fix the fp8_mqa_logits dim mismatch (#32652)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-01-20 18:48:07 +08:00
Cyrus Leung
7f1bcd18ff [3/N] Initialize MM components in context managers (I-L) (#32650)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 10:21:56 +00:00
Walter Beller-Morales
8be263c3fb [Core] Cleanup shm based object store on engine shutdown (#32429)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
2026-01-20 08:53:37 +00:00
Cyrus Leung
e1a34c3a5d [2/N] Initialize MM components in context managers (E-H) (#32641)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 08:12:56 +00:00
vllmellm
148117ea2e [Refactor] Make FP8 Linear Ops use kernel abstraction (#27814)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
2026-01-20 14:48:20 +08:00
Woosuk Kwon
e9c83cdc51 [Model Runner V2] Skip kernel launch for penalties & logit_bias (#32634)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2026-01-19 22:20:19 -08:00
Cyrus Leung
b75e85dede [1/N] Initialize MM components in context managers (A-D) (#32632)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 14:12:42 +08:00
Cyrus Leung
4753f3bf69 [Model] Use context managers for encoder- and LM-only mode (#32605)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2026-01-20 11:43:38 +08:00