Commit Graph
2199 Commits
Author SHA1 Message Date
Nicolò Lucchesi 164dca8d1e [Nixl] Separate transport-failure metrics from KV expiry (#55854)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-18 18:08:59 +02:00
Nicolò Lucchesi a7156060c1 [Core] Make parallel sampling (n>1) reqs admission atomic (#53936)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-18 18:08:44 +02:00
Simon Danielsson 70df48dc3d [Bugfix][KV Cache][GLM-5.3-Flash] Disable slot mapping kernel for the kpool tail buffer (#57317)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
2026-09-17 22:42:54 -04:00
Ren Yuzhou 7b94293627 [Bugfix][ROCm][KV Offload] Use private pinned tensors for CPU KV offload (#57160)
Signed-off-by: Yuzhou Ren <ryzcqu@outlook.com>
2026-09-18 02:35:23 +00:00
092bdd6d57 [Frontend][Core] Add release_kv_cache_memory() API (#44890)
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: AlanFokCo <alanfok2868@gmail.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Dakai An <77474977+andakai@users.noreply.github.com>
Co-authored-by: AlanFokCo <alanfok2868@gmail.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-18 07:12:12 +08:00
Wei Zhao ccde9c61e9 [Bugfix] Restore KV cache metadata GET method for external event consumer (#56925)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
2026-09-17 23:01:35 +00:00
Woosuk KwonandCodex 80447d2765 [Bugfix][DSv4.1] Fix FlashInfer DSpark non-causal attention (#57432)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
2026-09-17 15:14:37 -07:00
Misha Goin db7a24c230 [Perf] Add fused DFlash2 grouped convolution (#55960)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-09-17 21:38:59 +00:00
Doug Brown 2b02c6c29b [Model] Add Cohere2MoE Eagle3 auxiliary hidden states (#49819)
Signed-off-by: Doug Brown <doug@github.douggo.com>
2026-09-17 20:09:36 +00:00
Elvir CrnčevićOpenAI Codexmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Tyler Michael Smith
ac2f0ea82c [MoE][Bugfix] Skip SP padded rows in grouped MoE routing (#56079)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
2026-09-17 19:36:19 +00:00
67e5b0acc9 [Bugfix][HiSparse][NIXL] Import full blocks without tail prefill on D (#57049)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-09-17 15:26:10 -04:00
Michele Campi 6a344d8c85 [Bugfix][Metrics] Do not log a 0.0% prefix cache hit rate before any query (#54990)
Signed-off-by: Michele Campi <215741962+MicheleCampi@users.noreply.github.com>
2026-09-17 18:19:13 +00:00
Tyler Michael SmithOpenAI CodexOpenAI CodexMisha Goinmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
4f9a41ac94 [CI/Build][Hardware][NVIDIA] Add Rubin CUDA 13.4 nightly images (#55953)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-17 08:05:31 -07:00
Alexander Leeaoshen02Claude Opus 5aoshen02mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
9e1cd262cb [Bugfix] Use DP index for dense DP weight updates and EC CPU region (#56950)
Signed-off-by: lxy-alexander <lxy_alexander@outlook.com>
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-17 22:44:36 +08:00
Robert ShawandClaude Opus 5 861a299adc [Bugfix][Model Runner V2] Route dummy tokens to MoE experts during profiling (#57270)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-17 10:11:14 -04:00
CaiJohnandjohn 75c71390d5 [Bugfix] Escape control characters in xgrammar choice grammar (#48115)
Signed-off-by: john <6712432+CaiJohn@users.noreply.github.com>
Co-authored-by: john <6712432+CaiJohn@users.noreply.github.com>
2026-09-17 15:57:47 +03:00
Martín el CheikhandClaude 2e50824766 [Bugfix] Fall back to native sampling when FlashInfer cannot target the GPU (#48956)
Signed-off-by: martin el cheikh <martinelcheikh@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-09-17 12:27:54 +00:00
aoshen02andaoshen02 9ff08f9493 [Bugfix] Honor skip_reading_prefix_cache for KV connector hits (#57269)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
2026-09-17 03:46:28 -07:00
0d72627565 [Perf][EPD] Batch image requests per encoder (#57095)
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
Signed-off-by: Zhou ziheng <jiaranran2@gmail.com>
Co-authored-by: Zhou ziheng <jiaranran2@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-17 03:45:52 -07:00
Itay EtelisandOr Ozeri b6e7c1f1f0 [kv_offload] Skip scratch groups (#57145)
Signed-off-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-17 13:22:49 +03:00
40b40d1d39 [Bugfix][KV Offload] Register the offload region in chunks (#51081)
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Colton Ottley <coltonottley@gmail.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-17 13:19:56 +03:00
jiangkuaixue123andCodex de24e51908 [MM][V2] Enable encoder-only ViT CUDA graph capture (#56922)
Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-17 16:12:17 +08:00
2743dc4f92 [Feature][Multimodal] Add cross-encoder caching to Mooncake P2P (#56242)
Signed-off-by: Zhou ziheng <jiaranran2@gmail.com>
Co-authored-by: Tianyu Guo <guoty@inferact.ai>
Co-authored-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-17 13:16:41 +08:00
MattandClaude Code 68f2c7e74f [ROCm][CI] Fix Nixl+Offloading PD edge cases on TheRock image (#57249)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
2026-09-16 22:56:13 -05:00
Itay EtelisandOr Ozeri 9854b580df [Bugfix][KV Offload] Compact canonical MLA rows (#56799)
Signed-off-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-17 06:24:06 +03:00
omerpaz95 fa3622a4a1 [EC Connector] Add Metrics Collection (#54960)
Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
2026-09-17 10:36:23 +08:00
Oxana KorzhandAndreas Karatzas 2307a1d16c [Core] Don't issue a blocking collective RPC during engine handshake (#57226)
Signed-off-by: okorzh <okorzh@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-16 21:30:59 -05:00
Chuan (Richard) LiandCursor f730a93d2b [Scheduler] Add --max-num-active-seqs to cap RUNNING admission (#56758)
Signed-off-by: Li <chuali@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-17 10:22:12 +08:00
Jiangyun ZhuandCodex b1f9ebc0c3 [Test][Core] Add hybrid model prefix cache hit-rate coverage (#57127)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-16 19:17:45 -07:00
dongluwandAndreas Karatzas 19b6ff62f2 [ROCm][Bugfix] Ignore descales for unquantized AITER caches (#56726)
Signed-off-by: donglu <donglu@cohere.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-09-17 01:29:50 +00:00
Thillai Chithambaram a615f53364 [Bugfix][Metrics][MFU] Size activation traffic from the model dtype (#57070)
Signed-off-by: Thillai Chithambaram <thillaichithambaram.a@gmail.com>
2026-09-17 00:23:28 +00:00
Robert ShawandClaude 6c3d9816af [BugFix][KV Connector] Fix Deadlock with KVConnector + MTP under KV Pressure (#57104)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-09-16 22:22:07 +00:00
24a63b3340 [CI][Bugfix] Initialize _transfer_layer_group_ids in region_pull_worker fixture (#57211)
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>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-09-16 21:20:28 +00:00
Nicolò Lucchesi fc8132a5e5 [Bugfix] Fix np.float64 leaking into the KV transfer metrics log (#57068)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-16 18:09:05 +00:00
9f9e1dac26 [Bugfix][Model] Restore causal image SWA for DeepSeek V4.1 (#57152)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
2026-09-16 18:09:00 +00:00
Harry MellorandClaude Opus 5 651a88c09a [CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 10:57:24 -07:00
Harry MellorandClaude Opus 5 8c1557a79c Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-16 16:44:29 +00:00
Nicolò Lucchesi 804e5377aa [Bugfix][HiSparse][PD] Align region-mapped pulls across logical block sizes (#57077)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-16 18:39:07 +02:00
Robert ShawandClaude 42919b49c5 [P/D] Report prefill worker cache hits in prompt_tokens_details (#54222)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-09-16 15:23:31 +00:00
Nicolò Lucchesi 8b1d188046 [Bugfix][Mooncake] Report request-level KV load failures under HMA (#56855)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-09-16 14:55:40 +02:00
f37c550bf6 [Feature][Frontend] Expose effective attention block size for DCP (#56538)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Signed-off-by: Julien Darve <jdarve@NVIDIA.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-09-16 08:29:43 +00:00
Li, Jiang b68408043d [Bugfix][CPU] Add per-tensor FP8 W8A16 kernel to fix Ministral crash on CPU (#56985)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2026-09-16 15:49:17 +08:00
MINJUN GILandOr Ozeri f12fe10c5c [Bugfix][KV Offload] Track cache recency once per request (#51787)
Signed-off-by: mindungil <alswnsrlf12@naver.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-16 10:47:26 +03:00
Wei Zhao f30a195bbb [Bugfix] Fix incorrect Mamba block allocation estimate that prevents request admission (#57050)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
2026-09-16 07:23:20 +00:00
freyfwtCodexmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Jiangyun Zhu
18553c5c9f [Kernel] Use Murmur3 RNG for Gumbel sampling (#51367)
Signed-off-by: freyfwt <110148731+freyfwt@users.noreply.github.com>
Signed-off-by: freyfwt <freytian1996@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>
2026-09-15 23:52:26 -07:00
0f8fa53acf [Bugfix][KV Offload] Check cgroup memory before SHM allocation (#54014)
Signed-off-by: Alex <jihui.huang@daocloud.io>
Signed-off-by: AlexHuang <alex.tech.lab@outlook.com>
Signed-off-by: Alex <alex.tech.lab@outlook.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
2026-09-16 09:17:50 +03:00
Jiangyun ZhuandTJian 4fe9e6f6e5 [Refactor][GLM-5.3-Flash] Move sparse_attn_indexer_kpool into the model folder and split AMD/NVIDIA (#55358)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
2026-09-16 05:50:35 +00:00
961c5b6b7e [Bugfix][KV Offload] Restore MTP-retained sliding-window history (#56709)
Signed-off-by: jacklin78911-collab <jacklin78911@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-16 08:14:09 +03:00
alberto 75dc588269 [KV Offload] Add per-request max_load_tokens control (#55885)
Signed-off-by: Alberto Perdomo <aperdomo@redhat.com>
2026-09-16 06:57:38 +03:00
Qiming ZhangandKunshang Ji 4ace5cd9d8 [XPU] fix_test_worker_memory_snapshot_for_xpu (#50097)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-09-16 11:05:43 +08:00