|
639461eda4
|
[RL][Sleep] Retain frozen weights across level-2 sleep (#57891)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-22 12:36:55 +08:00 |
|
|
Yicong Wang
|
c4d424c2e2
|
[Bugfix][Spec Decode] Cap DFlash/DSpark profiling query batch (#56448)
Signed-off-by: wangyicong <wangyicong@bytedance.com>
|
2026-09-22 12:36:32 +08:00 |
|
|
Bugen ZhaoandCodex
|
ff3c9cba3f
|
[Rust Frontend] Add MiMo V2.5 parser support (#57933)
Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-22 04:27:09 +00:00 |
|
|
siyuandIsotr0py
|
c723a831a8
|
[Fast Start] Cache the MTP draft model in a separate daemon group (#57312)
Signed-off-by: liusy58 <mg21330037@smail.nju.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-22 03:13:38 +00:00 |
|
|
|
f07e227ee9
|
[Docker] Expose bundled vllm-rs on PATH (#57606)
Signed-off-by: Alec Flowers <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-21 20:03:03 -07:00 |
|
|
Chaojun ZhangandCopilot
|
1fee69838e
|
[XPU] Fix Nemotron FP8 LM-eval config: drop CUDA-only moe_backend and wire to new Buildkite job (#49685)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
2026-09-22 10:05:26 +08:00 |
|
|
|
e9f169d16b
|
[CI] Add pre-commit check that new tests are tethered to Buildkite jobs (#54867)
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com>
Signed-off-by: Turner <doubleujabbour@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-21 18:36:45 -07:00 |
|
|
cherry77-cloudandzjy0516
|
79468c20ef
|
[Bugfix][GDN] Fix stateless first-chunk classification (#51565)
Signed-off-by: taking-lying-flat <1615405@qq.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-09-22 09:11:49 +08:00 |
|
|
Navjot SinghandCodex
|
0bce411a07
|
[Bugfix] Annotate MTP draft KV cache groups positionally on the hybrid grouping path (#55390)
Signed-off-by: Navjot Singh <navjot.singh@shopify.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-22 00:31:26 +00:00 |
|
|
|
a369a7becc
|
[Perf][Attention] Reduce GLM sparse MLA preparation overhead (#57458)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
|
2026-09-21 17:24:25 -07:00 |
|
|
Robert ShawandRobert Shaw
|
c64b15cde5
|
[Scheduler] Soften Long Prefill Tokens Threshhold (#57951)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-09-21 17:19:42 -07:00 |
|
|
|
78d7836525
|
[CI] Split (H200) LM Eval Large Models into per-model jobs (#57965)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-21 17:19:17 -07:00 |
|
|
Taneem Ibrahim
|
7d06dd1ffa
|
[Pooling] MRV2 pooling shutdown model ref (#57737)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-21 16:54:57 -07:00 |
|
|
|
13058faa49
|
[Frontend] Add reusable TP1 initialized-engine snapshots (#51360)
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: elehayym <52448798+Yuzu23@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-21 23:18:49 +00:00 |
|
|
Garrett GoonandClaude Opus 5
|
8bf051cd51
|
[Bugfix][Kernel] Skip the fused silu-mul block-quant fast path when a swiglu clamp is set (#57984)
Signed-off-by: Garrett Goon <garrett@primeintellect.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-21 22:38:38 +00:00 |
|
|
vllm-agentandkimi-no-na-wa
|
8644d2af2f
|
[CI][Build] Harden triton-cpu sleef submodule fetch in CPU image build (#57871)
Signed-off-by: kimi-no-na-wa <kimi-no-na-wa@users.noreply.github.com>
Co-authored-by: kimi-no-na-wa <kimi-no-na-wa@users.noreply.github.com>
|
2026-09-21 15:30:14 -07:00 |
|
|
|
382970ee6c
|
[Kimi-K3][AMD] Return KDA and MLA projection outputs directly (#50592)
Signed-off-by: Liuyinfeng01 <yinfeliu@amd.com>
Co-authored-by: Liuyinfeng01 <199041580+LiuYinfeng01@users.noreply.github.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-21 15:44:41 -05:00 |
|
|
Nils Mattesonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9fe1cbd463
|
[Docker] Use zstd for CI images and offer a Docker Hub variant (#55608)
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-21 13:40:15 -07:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
12972ae40b
|
[Bugfix][ROCm] Reject unsupported EP for monolithic AITER MXFP4 MoE (#57866)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 15:30:21 -05:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
9179bcd416
|
[Bugfix][MoE] Reject hash routing for unsupported monolithic backends (#57867)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 16:28:35 -04:00 |
|
|
Nicolò Lucchesi
|
54020c3c3e
|
[Engram] Drop redundant VLLM_PLE_CPU_OFFLOAD env var (#57937)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-09-21 20:16:02 +02:00 |
|
|
Mikko Tukiainenandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
17322375a2
|
[ROCm][Perf] Route the fused shared-expert gate GEMM through the platform dispatcher (#54185)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-21 17:17:55 +00:00 |
|
|
Nicolò Lucchesi
|
fba33e39cb
|
[Docs] Add an Engram feature page explaining Engram usage in vLLM (#57910)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-09-21 17:15:28 +00:00 |
|
|
Karen Chung
|
986e217158
|
[Feature] Add first-class KV hints request envelope for programmatic KV management (#53423)
Signed-off-by: Karen Chung <karenc@nvidia.com>
|
2026-09-21 09:56:11 -07:00 |
|
|
djramicandAndreas Karatzas
|
4f14516790
|
[ROCm][CI] Use ROCm backend for DeepSeek V4.1 ViT test (#57931)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-21 16:39:31 +00:00 |
|
|
Cyrus Leung
|
7853700d4c
|
[MM] Move get_dummy_processor_inputs into MM processor (#57967)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-09-21 09:39:20 -07:00 |
|
|
Sahil PatelandCyrus Leung
|
4e61ad8ee1
|
[Bugfix] unskip InternViT test for transformers v5 compatibility (#55767)
Signed-off-by: sahil <sahil@example.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-21 09:38:25 -07:00 |
|
|
|
874a6b5a06
|
[ROCm] Refactor tuned gemms (#55001)
Signed-off-by: Andy Friedrich <afriedri@amd.com>
Signed-off-by: afriedri <afriedri@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-21 16:30:16 +00:00 |
|
|
Lucas WilkinsonandOpenAI Codex
|
8c0825090d
|
[Bugfix][NIXL] Fix DCP pulls across MLA cache regions (#57389)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 11:57:49 -04:00 |
|
|
LucainandClaude Opus 5
|
6b858751f6
|
[docs] Fix legacy hf CLI references (vllm) (#57958)
Signed-off-by: Wauplin <lucainp@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-21 15:32:27 +00:00 |
|
|
Tony Lin
|
dc479a2d83
|
[Bugfix] Fix external LB DP rank handling when replicas share nodes (#53743)
Signed-off-by: Tony Lin <tony.lin@intel.com>
|
2026-09-21 17:19:14 +02:00 |
|
|
Tuukka Sarviandlarryli2-amd
|
e34685dfc0
|
[ROCm][DSv4] Enable DSpark adaptive verification (#52362)
Signed-off-by: Tuukka Sarvi <tuukka.sarvi@amd.com>
Signed-off-by: larryli2-amd <larryli2@amd.com>
Co-authored-by: larryli2-amd <larryli2@amd.com>
|
2026-09-21 10:03:41 -05:00 |
|
|
sfigs
|
21aa17c128
|
[Bugfix][Frontend] Accept diarized transcription responses in run-batch (#57948)
Signed-off-by: Sergio Figueras <sergio@yourecm.com>
|
2026-09-21 14:55:38 +00:00 |
|
|
Taneem Ibrahim
|
887cf91e30
|
[Pooling] Fix normalization of chunked long-text embeddings (#57498)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-21 10:46:39 -04:00 |
|
|
Cyrus Leung
|
c8824a1e42
|
[MM] Move supports_multimodal_inputs and cache out of registry (#57913)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-09-21 07:43:07 -07:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
7488b5780f
|
[ROCm][Tests] Reduce host memory when downcasting FP32 HF references (#57869)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 22:42:47 +08:00 |
|
|
Martin Hickey
|
8b98b7d0b4
|
[Frontend] Add streaming parity tests and docs for derender (#57922)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
|
2026-09-21 14:13:52 +00:00 |
|
|
Hotragn PettuganiandClaude Opus 5
|
606d124b37
|
[Bugfix][Multimodal] Tolerate malformed EXIF in Molmo 2 image preprocessing (#57234)
Signed-off-by: hotragn <hotragn.pettugani_2024@woxsen.edu.in>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-21 06:27:40 -07:00 |
|
|
Chaojun ZhangandKunshang Ji
|
db7f1f6714
|
[CI][XPU] Deselect Ray UT in XPU V1 test Job (#57889)
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-09-21 20:54:58 +08:00 |
|
|
Juan Pérez de AlgabaandCursor
|
7268f6e38e
|
[Security] Prefer fresh multimodal payloads over a stale receiver cache (#57833)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-21 12:50:48 +00:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
82daf9f575
|
[CI][ROCm] Add ten AMD parity groups (#57876)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 11:08:06 +00:00 |
|
|
CaiJohnandjohn
|
15859bb3a1
|
[Test] Organize structured output utility tests (#57545)
Signed-off-by: john <6712432+CaiJohn@users.noreply.github.com>
Co-authored-by: john <6712432+CaiJohn@users.noreply.github.com>
|
2026-09-21 13:56:28 +03:00 |
|
|
Fangzhou AiandCursor
|
04c1f4a407
|
[Bugfix][ROCm][DSv4.1] Disable SWA bounded replay on ROCm (#57906)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-21 10:29:14 +00:00 |
|
|
|
0b7f11a1ee
|
[AuxOutput] Add block-keyed storage for routed-expert outputs (#45635)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-21 10:25:05 +00:00 |
|
|
djramic
|
0aee727ff6
|
[CI][ROCm] Increase timeout for MI300 Distributed DP Extended (#57903)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-09-21 04:18:59 -05:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
8902dbb177
|
[CI][ROCm] Mirror remaining portable suites without duplicate coverage (#57877)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 04:16:26 -05:00 |
|
|
|
b8cf275382
|
[AMD][Minimax-M3][perf] Enable packed LBHNC AITER QK-norm fusion for MiniMax-M3 on ROCm (#54535)
Signed-off-by: Wei-Ting Liao <wei-ting.liao@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-21 16:38:30 +08:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
f05b88751e
|
[CI][ROCm] Make Python-only installation failures blocking (#57870)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-21 08:29:02 +00:00 |
|
|
|
76ffb0d374
|
[Model][Engram] Share host tables across co-located DP replicas by default (#57651)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-09-21 08:26:56 +00:00 |
|
|
akii96
|
0ff0477ff9
|
[Perf][ROCm] Add a ROCm path for Hy4 and compile the backbone (#57526)
Signed-off-by: Aakif Nawaz <aakif.nawaz@amd.com>
|
2026-09-21 08:20:43 +00:00 |
|