 Guanxin LiandClaude Opus 5
|
925ea7e60f
|
[CI][Test] Seed the DeepEP v2 MoE workers, not just the parent (#50589)
Signed-off-by: Guanxin Li <guanxinl@nvidia.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-14 16:01:24 -04:00 |
|
|
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 |
|
|
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 |
|
|
stefankoncarevic
|
83ded8d839
|
[Test][LoRA] Speed up the LoRA test job (#52331)
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
|
2026-08-14 12:08:41 -05:00 |
|
|
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 |
|
|
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 |
|
|
Jee Jee Li
|
69e0e58da1
|
[Doc] Update model support information (#52289)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-14 09:47:30 +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 |
|
|
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 |
|
|
ccaadaroandLi, Jiang <jiang1.li@intel.com>
|
bda4c3e8ee
|
[CPU] Fold the MXFP4 block scale in 2 instructions instead of 4 (#51583)
Signed-off-by: ccaadaro <ccanadar@unex.es>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-08-14 08:19:21 +00:00 |
|
|
|
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 |
|
|
|
59d1af5698
|
Detect ROCm wheel variant from environment for precompiled wheels. (#49365)
Signed-off-by: aarushjain29 <Aarushi.Jain2@amd.com>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-08-13 21:19:20 -07:00 |
|
|
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 |
|
|
|
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 |
|
|
Qiming Zhang
|
d18bb7b390
|
[UT] fix device of test_outputs.py (#52237)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-08-14 11:29:54 +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 |
|
|
|
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 |
|
|
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 |
|
|
|
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 |
|
|
stefankoncarevic
|
11c3fa4adc
|
[Bugfix][ROCm][CI] Give the AITER MLA decode metadata stub its MLA dims (#52139)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-08-13 13:35:00 -05:00 |
|
|
|
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 |
|
|
Andreas Karatzas
|
b96bcd0b47
|
[ROCm][CI] Solidify entrypoint LLM lifecycle (#51280)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-13 12:24:02 -05:00 |
|
|
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 |
|
|
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 |
|
|
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 |
|
|
|
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 |
|
|
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 |
|
|
|
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 |
|
|
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 |
|
|
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 |
|
|
Juan Pérez de Algaba
|
37c3bdf5a7
|
fix(security): enforce audio decode duration limit in NanoNemotronVL (#50221)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-08-13 03:31:55 -07:00 |
|
|
Thomas Ortner
|
b8baa31a28
|
Hardware-agnostic model definition via HF transformer backend (1/N) (#49458)
Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>
|
2026-08-13 11:21:50 +01:00 |
|
|
|
50ba4bc6b2
|
[Feature] Mask Replay (#49577)
Signed-off-by: vx120 <893600387@qq.com>
Signed-off-by: vx120 <57470515+vx120@users.noreply.github.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-13 08:44:31 +00:00 |
|
|
Frank
|
7bc1660bd6
|
[Misc] Use VLLMValidationError in pooling input validation (#51931)
Signed-off-by: frank-suwen <suwenw2@outlook.com>
|
2026-08-13 06:13:25 +00:00 |
|
|
|
903d2efe7e
|
[Attention][MLA] Fuse Kimi-K3 chunked-context K/V packing (#51772)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-12 22:42:57 -07:00 |
|
|
kx
|
2ac1f683f1
|
[BugFix] Reserve the bonus query slot in DFlash scheduling budget (#51256)
Signed-off-by: HF-001 <1670186653@qq.com>
|
2026-08-13 03:50:23 +00:00 |
|
|
Lucas WilkinsonandOpenAI Codex
|
79f3183f86
|
[Bugfix] Bound KV block zeroing launch geometry (#52058)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-13 03:42:26 +00:00 |
|
|
Ziqi Fan
|
15227b934a
|
[Bugfix][KV Offload] Emit self-describing CPU events at KV-group block granularity (#51614)
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
|
2026-08-12 20:28:15 -07:00 |
|
|
Ziqi Fan
|
f9a0f629bd
|
[KV Offload] Expose data-parallel topology to offloading backends (#51879)
Signed-off-by: Ziqi Fan <ziqif@nvidia.com>
|
2026-08-12 20:27:26 -07:00 |
|
|
Julien Debache
|
6e502b62cb
|
fix and test EPLB balancedness calculation (#51813)
Signed-off-by: jdebache <jdebache@nvidia.com>
|
2026-08-12 20:27:22 -07:00 |
|
|
|
61826c1c6f
|
[Hardware][Power] Unqualized MoE Backend for Power (VSX) (#51624)
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Antigravity <antigravity@google.com>
|
2026-08-13 10:56:09 +08:00 |
|
|
Kevin H. LuuandOpenAI Codex
|
8eb35c5217
|
[CI] Mirror external test assets in vLLM S3 (#52064)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-08-13 02:08:59 +00:00 |
|
|
|
5936bac7d7
|
[Bugfix] Report FULL_ATTENTION for uniform-base UniformTypeKVCacheSpecs groups instead of UNKNOWN (#51218)
Signed-off-by: Yifan Jiang <19356972+yifjiang@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-08-13 01:25:23 +00:00 |
|
|
Wentao Ye
|
23f360edaa
|
[CI Bug] Fix ci moe test (#52009)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-12 21:28:53 +00:00 |
|