 Canlin Guo
|
bc2d63e650
|
[Kimi K3][Kernel] Enable low-latency decode GEMM dispatch on SM100 (#53534)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-25 16:32:28 -07:00 |
|
|
Almog Tavor
|
bc39ded3c4
|
[Bugfix][KV Offload] Defer request-level cascade of in-flight primary keys (#53329)
Signed-off-by: almogtavor <almogtavor@gmail.com>
|
2026-08-25 23:20:03 +00:00 |
|
|
Wentao Ye
|
0e30bd62fe
|
[CI Bug] Fix kimi test AssertionError: Aligned Mamba state indices must be precomputed (#53766)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-25 15:06:14 -04:00 |
|
|
Wentao Ye
|
384d079697
|
[Perf] Autotune batch invariance triton kernel in blackwell, 33.6% E2E latency reduction (#53649)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-25 15:06:01 -04:00 |
|
|
Nick Hill
|
e6cc0899b6
|
[Bugfix][MRV2] Run cudagraph memory profiling in a throwaway graph pool (#53682)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-25 18:52:15 +00:00 |
|
|
Misha GoinandOpenAI Codex
|
c9331d8064
|
[CI] Preserve Rust Docker cache across commits (#53290)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-25 11:13:36 -07:00 |
|
|
Moe Huzaifa
|
299ebd094a
|
[Bugfix][Multimodal] Reject malformed base64 audio with 400 instead of 500 (#53744)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
|
2026-08-25 17:31:42 +00:00 |
|
|
Misha Goin
|
7de96050c5
|
[Spec Decode] Enable adaptive DSpark on SM100 sparse MLA (#52783)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-08-25 13:31:15 -04:00 |
|
|
Moe Huzaifa
|
217a0b5cef
|
[Bugfix][Frontend] Apply the stop string limit to Cohere requests (#53750)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
|
2026-08-25 16:41:08 +00:00 |
|
|
Moe Huzaifa
|
3e833933dc
|
[Bugfix][Frontend] Keep credentials out of the Rust frontend launch log (#53738)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
|
2026-08-25 16:32:12 +00:00 |
|
|
Moe Huzaifa
|
19406fae28
|
[Bugfix][Tokenizer] Replace bare asserts in the DeepSeek V4 encoder (#53747)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
|
2026-08-25 16:30:23 +00:00 |
|
|
Luke Alonso
|
3454335f7b
|
[Bugfix] Resolve B12X modules before Dynamo tracing (#53326)
Signed-off-by: Luke Alonso <lalonso@gmail.com>
|
2026-08-25 09:20:15 -07:00 |
|
|
Wentao Ye
|
41729fc53b
|
[K3 Perf] Optimize k3 mamba metadata preparation, 6.6~7.6x kernel performance improvement (#52388)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-25 11:00:28 -04:00 |
|
|
Naveenraj KamalakannanandBenjamin Chislett
|
d5cadcee86
|
[Feature][DSpark]: Logprobs adaptive verification (#52242)
Signed-off-by: Naveenraj Kamalakannan <therealnaveenkamal@gmail.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-08-25 10:22:33 -04:00 |
|
|
|
ca29cd48ba
|
[Quantization][Humming] Support MXFP4 weight + block-FP8 activation for MoE (#51332)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-25 10:21:00 -04:00 |
|
|
Elvir Crnčević
|
afc91fa0d2
|
[Profiler] Fix start_profile permanently no-op after max_iterations auto-stop (#51839)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
|
2026-08-25 08:13:29 -04:00 |
|
|
djramic
|
d9fbe526c0
|
[ROCm][CI] Skip ModernBERT FP8 MTEB test when no FP8 ScaledMM kernel exists (#53589)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-08-25 08:07:09 +00:00 |
|
|
Tianyu Guo
|
12c84b98dd
|
[Config][EC] Normalize producer-only encoder config (#53656)
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
|
2026-08-25 07:53:04 +00:00 |
|
|
Jiahao LiangandChauncey
|
59d7fc92ea
|
[Bugfix][DeepSeek V4] Handle trailing system messages in prompt rendering (#51262)
Signed-off-by: jiahaoliang <gzliangjiahao@gmail.com>
Signed-off-by: Jiahao Liang <gzliangjiahao@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-08-25 07:49:44 +00:00 |
|
|
Jiatai WangandOpenAI Codex
|
06ecec7a84
|
[Bugfix][MM] Fix JinaVL processing cache order (#53553)
Signed-off-by: JiataiWang <wangjiatai@proton.me>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-25 00:03:05 -07:00 |
|
|
wang.yuqi
|
735daf8ef6
|
[Frontend] Move cli_args.py and dp_supervisor.py out openai folder (#53659)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-08-25 07:02:32 +00:00 |
|
|
|
c74dd2d208
|
[Bugfix][MRV2] Dispatch uniform decode to a padded FULL cudagraph (#53407)
Signed-off-by: Xiaohu Guo <Xiaohu.Guo@amd.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: xiaohuguo2023 <149615094+xiaohuguo2023@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-08-25 06:59:38 +00:00 |
|
|
|
48d7132962
|
[Model] Migrate FlexOlmo, Olmo3 and Hunyuan V1/VL to the Transformers modeling backend (#53615)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-08-24 22:39:05 -07:00 |
|
|
Karan Shelar
|
a9a17e7095
|
Dflash2 load fix (#53435)
|
2026-08-24 21:32:43 -07:00 |
|
|
|
af119619c4
|
Exclude the cpu backend from vLLM's active-Triton-driver count (#53530) (#53530)
Signed-off-by: Minjang Kim <minjang@meta.com>
Co-authored-by: Autopilot Bot <noreply+1608173377072046@fb.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-25 04:13:13 +00:00 |
|
|
|
8fe9317f2e
|
[Model][MoE] DeepSeek-V4: add opt-in FlashInfer moe_ep expert backend (#49636)
Signed-off-by: Md Saidul Hoque Anik <mhoqueanik@nvidia.com>
Signed-off-by: Anerudhan Gopal <agopal@nvidia.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Anerudhan Gopal <agopal@nvidia.com>
|
2026-08-25 03:35:01 +00:00 |
|
|
Moe Huzaifa
|
d3e2888c75
|
[Bugfix][Frontend] Redact hf_token in the non-default args log (#53625)
Signed-off-by: mhuzaifa3 <mhuzaifa3@outlook.com>
|
2026-08-25 03:06:46 +00:00 |
|
|
Ziming HuangandRoger Wang
|
d4c4ceb31e
|
[Bugfix][NIXL] Fix Mamba prefill truncation ordering (#53523)
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-08-24 19:13:27 -07:00 |
|
|
kiroxuandOpenAI Codex
|
07ef21bc69
|
[Kernel][Perf] Enable fused QK-norm + partial MRoPE + gate for Qwen3.6 (#52676)
Signed-off-by: kiroxu <148877251+BabyDrangoner@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-24 18:28:49 -07:00 |
|
|
drakoshaandClaude
|
9bf0d4717e
|
[Bugfix] Keep grid dims for XD-RoPE models on a prefix-cache hit (#53456)
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-25 01:14:32 +00:00 |
|
|
|
7ca336929c
|
[Model] Remove ten deprecated model architectures (#53608)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-24 17:06:00 -07:00 |
|
|
rasmith
|
a0f1b9ad05
|
[CI][The Rock] Increase flex attention abs tol (#53646)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
|
2026-08-24 23:57:03 +00:00 |
|
|
Giancarlo Delfin
|
d154d90d6c
|
[Model Runner V2] batch-sharded sample (#50465)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
|
2026-08-24 15:49:57 -07:00 |
|
|
Juan Pérez de Algaba
|
0d7d5ed0b2
|
fix(security): enforce VLLM_MAX_AUDIO_CLIP_FILESIZE_MB on all audio paths (#53561)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-08-24 21:37:02 +00:00 |
|
|
Khushali Desai
|
23ab0cfdbc
|
speculative decoding under tensor parallelism (TP>1) , workspace creation select max hidden dim of target and draft model (#52193)
Signed-off-by: khushali9 <khushali.desai9@gmail.com>
|
2026-08-24 21:33:36 +00:00 |
|
|
Wentao Ye
|
f59bb0bd8c
|
[Refactor] Refactor batch invariance folder (#53619)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-24 14:31:36 -07:00 |
|
|
Guan-Ming Chiu
|
6a9c69fa85
|
[Attention][Spec Decode] Support varlen trtllm-gen decode for adaptive verification (#52157)
Signed-off-by: Guan-Ming (Wesley) Chiu <105915352+guan404ming@users.noreply.github.com>
|
2026-08-24 14:43:57 -04:00 |
|
|
Prudhvi Vudaandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
342b8ebd8b
|
[Bugfix][Multimodal] Encode text in mixed CLIP/SigLIP pooling batches (#53165)
Signed-off-by: Prudhvivuda <prudhvi12042001@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-24 10:45:42 -07:00 |
|
|
Jee Jee LiandCyrus Leung
|
4f686e182a
|
[MISC] Cleanup deprecated parameters (#53559)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-08-24 10:19:04 -07:00 |
|
|
Lio Einaudiandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
7797b6022c
|
[Kernel][Perf] Per-architecture tuned configs for batch-invariant persistent matmul (~3x decode kernels on RTX 4090D/H20) (#53247)
Signed-off-by: LioEinaudi <zhao3024667639@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-24 11:28:51 -04:00 |
|
|
Kevin H. LuuandCodex
|
4c56e62c85
|
[Bugfix][Kimi K3] Skip absent metadata during CUDA graph profiling (#53581)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-08-24 15:16:28 +00:00 |
|
|
Misha Goin
|
f620499ee3
|
[Bugfix][Spec Decode] Reapply group geometry for FlashAttention metadata (#53336)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-08-24 08:08:43 -07:00 |
|
|
wang.yuqi
|
9cef631f30
|
[Frontend] Move run_batch.py out openai folder (#53500)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-08-24 15:04:10 +00:00 |
|
|
Cyrus Leung
|
ecfa7bb373
|
[MM] Cache common token sequences (#53560)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-08-24 07:48:10 -07:00 |
|
|
石皮幼鸟andOpenAI Codex
|
4ca856b0b5
|
[Bugfix] Release worker RPC payload before next dequeue (#51979)
Signed-off-by: 石皮幼鸟 <2960474346@qq.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-24 07:27:36 -07:00 |
|
|
Taneem Ibrahim
|
79bb395eea
|
[Pooling] Improve BGE-M3 sync pooling throughput by up to 3.13% (#53464)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-08-24 08:33:32 -04:00 |
|
|
andrewbcohere
|
41ae917c12
|
Add Cohere ChatV2 render endpoint (#53219)
|
2026-08-24 12:27:57 +00:00 |
|
|
Tan ChaoandClaude
|
e239947777
|
[Bugfix][Frontend] Fix run_batch upload retrying on success and unawaited error body (#50588)
Signed-off-by: Chao Tan <chaos.tc@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-24 11:33:44 +00:00 |
|
|
Nicolò Lucchesi
|
0ecc284790
|
[Bugfix][Kernel] Handle kernel block sizes in V2 DCP slot mapping (#51031)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-08-24 07:28:38 +00:00 |
|
|
Ace EldeibandCodex
|
a047e2543d
|
Fix MNNVL Lamport mailbox publication and cleanup (#53000)
Signed-off-by: Ace Eldeib <aeldeib@coreweave.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-08-23 23:56:54 -07:00 |
|