 sroberts-amdandStacy Roberts
|
c794754062
|
[ROCm]Remove special-case SiTU support model-specific gating (#50597)
Signed-off-by: Stacy Roberts <sroberts@amd.com>
Signed-off-by: Stacy Roberts <robers23@utexas.edu>
Co-authored-by: Stacy Roberts <robers23@utexas.edu>
|
2026-08-14 13:38:04 -05:00 |
|
|
Connor CarpenterandNick Hill
|
f473870ecf
|
[Rust Frontend][gRPC] Add RL lifecycle control (#51316)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-14 11:32:39 -07:00 |
|
|
Nick Hill
|
3e3ceb1961
|
[Perf] Avoid more GPU<->CPU syncs in multimodal encoders (#52369)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-14 10:40:14 -07:00 |
|
|
James E T SmithandAndreas Karatzas
|
9b0ab5dd53
|
[ROCm][AMD] Enable preshuffled sparse indexing for 16-token blocks (#51216)
Signed-off-by: jamesETsmith <james.smith9113@gmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-14 12:38:14 -05:00 |
|
|
shanjiaz
|
e078a2238a
|
[Bugfix] Widen flashinfer.comm import guard so a failed import doesn't abort engine startup (#52241)
Signed-off-by: shanjiaz <zsjwpianpian@gmail.com>
|
2026-08-14 16:27:24 +00:00 |
|
|
Rahul ChalamalaandJanelle Cai
|
03a8d0b1ed
|
[Model][Spec Decode] Tap the pre-norm AttnRes mixture as the Kimi K3 DFlash aux state (#50487)
Signed-off-by: Rahul Chalamala <22563365+rchalamala@users.noreply.github.com>
Co-authored-by: Janelle Cai <janelle.cai@modal.com>
|
2026-08-14 09:03:42 -07:00 |
|
|
wangxiyuanandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
cdc4824a21
|
[Misc] Remove override_attention_dtype (#48684)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-14 11:15:43 -04:00 |
|
|
Qiming ZhangandAndreas Karatzas
|
1f7427bc0a
|
[UT][XPU] fix b12x UT (#52265)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-08-14 09:49:47 -04:00 |
|
|
Lucas WilkinsonandClaude
|
57bd0ed441
|
[5/N][KV-Cache Layout Refactor] Backend-published KV packing via customize_spec (#51704)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-14 09:47:55 -04:00 |
|
|
Zhuobin Huangandnodeeeeee
|
63a9a5010a
|
[Attention][DSA] Take the native decode path for MTP=3 on SM90 (#52164)
Signed-off-by: zobinHuang <zobin1999@gmail.com>
Co-authored-by: nodeeeeee <zhangkai.nodeee@gmail.com>
|
2026-08-14 10:09:51 +00:00 |
|
|
bastefaniak
|
20405bfb15
|
[Bugfix] Fix Cosmos3-Edge processor after transformers 5.15 release (#51989)
Signed-off-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
|
2026-08-14 10:46:46 +01:00 |
|
|
Isotr0pyandOpenAI Codex
|
66728feb1f
|
[MRV2][Multimodal] Enable encoder cuda graph for model runner v2 (#49852)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-14 09:33:21 +00:00 |
|
|
wang.yuqi
|
b8165e5e58
|
[Frontend] Consolidate entrypoint exception handler (#52261)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-08-14 09:27:24 +00:00 |
|
|
Fangchen LiandClaude Opus 5
|
103c419f04
|
[Perf][Frontend] Vectorize Cohere binary embedding bit-packing (#52277)
Signed-off-by: Fangchen Li <fangchen.li@outlook.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-14 09:15:59 +00:00 |
|
|
YiSheng5andKunshang Ji
|
3c8676aebb
|
[PP][XPU]Overlap async-scheduling PP sampled-token broadcast with compute (#51650)
Signed-off-by: yisheng <yi.sheng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-14 17:00:23 +08:00 |
|
|
|
6adad08767
|
Add Muse Glimmer model support (#51655)
Signed-off-by: Tiezhen Wang <tiezhen@inferact.ai>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Beto de Paola <betodepaola@meta.com>
Co-authored-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: zixi-qi <zixi@inferact.ai>
|
2026-08-14 12:28:56 +08:00 |
|
|
Tzu-Ling KanandClaude Opus 4.8
|
653cc6faca
|
[Bugfix][NIXL] Include transfer mode (push/pull) in the compatibility hash (#50620)
Signed-off-by: Tzu-Ling <tzulingk@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-08-14 12:11:22 +08:00 |
|
|
|
c05d75aaa9
|
[Bugfix][Refactor] Keep Qwen3Next layer boundaries sequence parallel (#50685)
Signed-off-by: kunzh <RimeK20@outlook.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-08-14 11:58:32 +08:00 |
|
|
|
1be3628367
|
[Kernel][Perf] Add fused CUDA post-conv MTP decode kernel for Qwen3.5 GDN (#51674)
Signed-off-by: Jie Fang <jief@nvidia.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-14 11:44:45 +08:00 |
|
|
Luke Alonso
|
3c79b1a8bf
|
[Kernel] Add B12X dense linear backends (#52016)
Signed-off-by: Luke Alonso <lalonso@gmail.com>
|
2026-08-13 19:48:33 -07:00 |
|
|
zofia
|
fe4c5dcd4c
|
[XPU] [Bugfix] process ragged weights in xpu linear backend (#52118)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
|
2026-08-14 09:11:43 +08:00 |
|
|
|
b216db3ed0
|
[Bugfix] Reject negative token ids as out-of-vocabulary (#51795)
Signed-off-by: Junhao Shen <junshen@nvidia.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-08-14 01:07:29 +00:00 |
|
|
|
827a2af806
|
[Kernel] Gemma-4 FA4 FP8 Kernel (#48666)
Signed-off-by: Qixiang Lin <qixiangl@nvidia.com>
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
Co-authored-by: Qixiang Lin <qixiangl@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-08-13 17:42:00 -07:00 |
|
|
Junhao ShenandClaude Opus 4.8
|
38f097fab8
|
[Bugfix] Reject NUL byte in structured_outputs.regex (#51796)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-08-14 00:08:36 +00:00 |
|
|
Giancarlo DelfinandClaude Fable 5
|
f80b66f548
|
[Model Runner V2][Spec Decode] Add KV cache support for multi-layer MTP (#50062)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-13 16:22:29 -07:00 |
|
|
bastefaniak
|
71b0da7c4e
|
[Bugfix] Fix .../mrope.py::apply_interleaved_rope() when torch.compile is used in torch==2.13 (#52005)
Signed-off-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
|
2026-08-13 22:08:40 +00:00 |
|
|
Benjamin Chislett
|
51def7848a
|
[Bugfix] Reapply 50869 (#52223)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-08-13 15:08:07 -07:00 |
|
|
Stan WozniakandThomas Parnell
|
63550515b4
|
[Bugfix] Correct prompt lengths for timed_traces benchmark (#45423)
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
|
2026-08-13 21:51:24 +00:00 |
|
|
|
b652dedd0c
|
[Attention] Fix FlashInfer SM12x prefill with sinks (#52148)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-08-13 14:25:09 -07:00 |
|
|
wangxiyuan
|
73b83949f7
|
[Platform] Add check_runner_kv_caches_multi_layer (#51633)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
|
2026-08-13 19:25:07 +00:00 |
|
|
|
c5b7c069a4
|
[ROCm] Defer tilelang import through its import from vllm.tilelang_utils import tilelang and relaxed has_tilelang (#51159)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-13 13:12:40 -05:00 |
|
|
yzong-rh
|
e6b2a8ad5e
|
[Bugfix][Structured Output] Mask request stop tokens in xgrammar until grammar terminates (#50595)
Signed-off-by: Yifan Zong <yzong@redhat.com>
|
2026-08-13 14:07:59 -04:00 |
|
|
fxmarty-amd
|
48825acc23
|
[Quantization] Remove dead QuantizationConfig.is_mxfp4_quant (#51793)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
|
2026-08-13 13:58:31 -04:00 |
|
|
Nick Iusiumbeli
|
83d4c6196a
|
[Bugfix] Declare SupportsEagle3 on KimiLinearForCausalLM (#52171)
Signed-off-by: Nick Iusiumbeli <nickuspro@gmail.com>
|
2026-08-13 16:22:50 +00:00 |
|
|
Harry Mellor
|
b245d8e73f
|
Apply logit softcapping in Transformers modelling backend (#52173)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-13 16:21:55 +00:00 |
|
|
Thien Tran
|
6014f9e672
|
[Kimi-K3] Add GEMM-RS for sequence parallelism (#52079)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-08-13 09:02:28 -07:00 |
|
|
Qiming Zhang
|
96acd473a7
|
[Bugfix][MiniCPM-V] Fix AssertionError in get_dummy_mm_data when passing VideoDummyOptions to _get_dummy_images (#52122)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-08-13 15:44:03 +00:00 |
|
|
Ali JaseemandClaude
|
64ca614fe4
|
[Bugfix] Fix --data-parallel-start-rank 0 being treated as unset in create_engine_config (#47692)
Signed-off-by: Syed Ali Jaseem <syedali0057@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-13 15:12:26 +00:00 |
|
|
Harry MellorandClaude Opus 5
|
80d6d557f3
|
Standardise weight tying on ParallelLMHead.tie_weights (#52147)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-13 15:10:09 +00:00 |
|
|
|
7553aac77b
|
[Frontend] Add routed-experts prompt offset (#51906)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-13 08:09:00 -07:00 |
|
|
vllmellm
|
f3c1638927
|
[ROCm] Enable V2 model runner for Kimi-K3 on ROCm (#51653)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2026-08-13 14:34:53 +00:00 |
|
|
Michael Goin
|
2d24355eb8
|
[Bugfix] Fix packed GDN decode launch for large batch-head grids (#52030)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-08-13 07:19:08 -07:00 |
|
|
范裕达
|
170592a931
|
[Bugfix] Disable sequence parallelism for Dots3 NOTE (#52172)
Signed-off-by: KurodaKanbei <mistergalahad@gmail.com>
|
2026-08-13 22:13:00 +08:00 |
|
|
|
95c9144424
|
[LoRA][Gemma4] Support vision tower LoRA (#42662)
Signed-off-by: bk-201 <joy25810@foxmail.com>
Signed-off-by: linitra24 <Joy25810@foxmail.com>
Signed-off-by: linitra24 <joy25810@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: linitra24 <joy25810@gmail.com>
|
2026-08-13 22:07:43 +08:00 |
|
|
zexplorerhj
|
8e1131e1d1
|
[Model] [Quantization] Add Ling hybrid MXFP4 routed experts support (#52114)
Signed-off-by: zexplorerhj <zhjoneson@163.com>
|
2026-08-13 21:46:53 +08:00 |
|
|
yang rui
|
152c913a63
|
[Frontend] Log output token IDs at DEBUG level (#52098)
Signed-off-by: ruirui6946 <142162413+ruirui6946@users.noreply.github.com>
|
2026-08-13 13:11:51 +00:00 |
|
|
Vineeta TiwariandVineeta Tiwari
|
015660da91
|
[Misc] Add missing return type annotations in outputs.py (#52145)
Signed-off-by: Vineeta Tiwari <vineeta.tiwari2@ibm.com>
Co-authored-by: Vineeta Tiwari <vineeta.tiwari2@ibm.com>
|
2026-08-13 12:58:45 +00:00 |
|
|
pmanczak
|
c4e969294e
|
[XPU] Add tuned Mamba SSU configs for Intel Arc Pro B70 (#50534)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
|
2026-08-13 12:36:55 +00:00 |
|
|
Taneem Ibrahim
|
d0ae25e2f2
|
[Bugfix] Preserve Anthropic disable_parallel_tool_use (#52021)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-08-13 08:25:55 -04:00 |
|
|
JasonCohere
|
5fee0a872d
|
chore: Upstream Cohere parser fixes + tests (#51998)
Signed-off-by: Jason Ozuzu <jasonozuzu@cohere.com>
|
2026-08-13 05:05:36 -07:00 |
|