|
e77daef89e
|
[Model] Support DeepSeek-V4.1-Flash (#56214)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: andyluo7 <andy.luo@amd.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-11 02:11:19 -07:00 |
|
|
Kevin H. LuuandOpenAI Codex
|
1cf6555214
|
[Bugfix] Pin EPLB and MLA host-to-device transfer buffers (#56138)
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-11 01:57:47 -07:00 |
|
|
|
d0dfe587d5
|
[Bugfix] Fall back to full decode graphs for noncompiled models (#55095)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-09-11 01:56:05 -07:00 |
|
|
|
fadfe1c7d4
|
[Bugfix][Core] Retire Mamba states across null gaps (#55450)
Signed-off-by: Luca Motz <luca.motz@icloud.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-11 15:50:47 +08:00 |
|
|
|
4b839c3378
|
[Attention] Extend XQA decode support on SM90 (#50439)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-11 06:19:55 +00:00 |
|
|
|
980c16c8e4
|
[PCP][Spec Decode] Adds PCP support for single-module MTP and replicated DSpark. (#56107)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-10 22:07:53 -07:00 |
|
|
|
ce08bb5b34
|
[Bugfix][Mooncake] Fix heterogeneous PP transfer completion (#56033)
Signed-off-by: wangyicong <wangyicong@bytedance.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-11 10:57:19 +08:00 |
|
|
YukioZzz
|
07b7553465
|
[Feature][SimpleCPU] Load fine-grained hybrid prefix hits (#54736)
Signed-off-by: Yichao Zhu <Yichao.Zhu@amd.com>
|
2026-09-10 20:36:37 -05:00 |
|
|
|
828f4f19b4
|
[ROCm][Bugfix] Route GLM-5.3-Flash MTP through ragged sparse MLA (#55239)
Signed-off-by: jamesETsmith <james.smith9113@gmail.com>
Signed-off-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-10 20:13:14 -05:00 |
|
|
焦恺文
|
84030bbe3d
|
[Bugfix][Core] Stop zero-progress preemption cascades for deferred KV frees (#49675)
Signed-off-by: LearningMachine621 <147347705+LearningMachine621@users.noreply.github.com>
|
2026-09-11 00:40:10 +00:00 |
|
|
Julien Denize
|
983b7e28c9
|
[Bugfix] Avoid MistralCommonBackend for HF tokenizers (#54192)
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
|
2026-09-10 17:57:44 +00:00 |
|
|
|
8359e15aae
|
[ROCm][Feature] Support KV connectors with ROCM_AITER_UNIFIED_ATTN (#53695)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
Signed-off-by: Simon Danielsson <70206058+simondanielsson@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-10 12:48:42 -05:00 |
|
|
Nick Hill
|
e6cb56337b
|
[Core] MRV2 support for fast-prefill (#56145)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-10 10:36:04 -07:00 |
|
|
Rita Brugarolasandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
6ee5bb0a0b
|
[DCP][Kernel][Perf] Fuse the empty-shard LSE mask into the A2A pack kernel (#54889)
Signed-off-by: Rita Brugarolas Brufau <rita.brugarolasbrufau@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-10 11:43:00 -04:00 |
|
|
Lucas WilkinsonandNicolò Lucchesi
|
93911fcf68
|
[NIXL][PCP] Report replicated-PCP ranks > 0 as done sending instead of hiding them (#53903)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
|
2026-09-10 12:58:05 +02:00 |
|
|
Toby Mao
|
b28c3e1568
|
[BugFix] Retain both replay boundaries so an EAGLE resend of a block-aligned prompt still hits (#54713)
Signed-off-by: tobymao <toby.mao@gmail.com>
|
2026-09-10 16:39:24 +08:00 |
|
|
|
83990f5bcc
|
[Bugfix][MRV2] Initialize DCP metadata after batch partitioning (#55212)
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Signed-off-by: Ziyang Zhang <hafuhafu@qq.com>
Signed-off-by: Sy03 <1370724210@qq.com>
Co-authored-by: Raphael Rialland <raphael.rialland@mistral.ai>
Co-authored-by: Ziyang Zhang <hafuhafu@qq.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-10 06:50:09 +00:00 |
|
|
Yunzhu LuandIsotr0py
|
442d36031c
|
[MM][CG] Enable encoder CUDA Graph for MiniCPM-V (#42785)
Signed-off-by: YunzhuLu <lucia.yunzhu@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-10 06:28:48 +00:00 |
|
|
Li, Jiang
|
c3ccc0e957
|
[Model] Add DeepSeek-V4 CPU backend (#55355)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-09-10 14:14:48 +08:00 |
|
|
Tianyu Guo
|
479611c0c6
|
[Frontend][EPD] Use JSON arrays for multimodal metadata (#56090)
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
|
2026-09-10 05:04:14 +00:00 |
|
|
Wei ZhaoandOpenAI Codex
|
8c87c333b8
|
[Perf] Fix TRTLLM ragged prefill perf regression (#55499)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-09 20:38:20 +00:00 |
|
|
|
83fe99399e
|
[Spec Decode] Add NVFP4 DSpark gathered top-k projection (#55713)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-09 17:33:46 +00:00 |
|
|
Harry MellorandClaude Opus 5
|
719284fe15
|
[Core][Model] Unify XD-RoPE into M-RoPE and derive the channel count (#56078)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-09 09:23:30 -07:00 |
|
|
|
c55e15a44e
|
[Structured Output] Keep invalid structured-output requests from stopping the engine (#51450)
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-09-09 15:32:01 +00:00 |
|
|
Ronen Schaffer
|
138d137b5b
|
[Refactor][kv_offload]: rename block→chunk (#52615)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
|
2026-09-09 17:45:49 +03:00 |
|
|
Yicong WangandOpenAI Codex
|
d2906091bf
|
[Bugfix] Fix Mooncake heterogeneous TP with replicated GQA heads (#52516)
Signed-off-by: wangyicong <wangyicong@bytedance.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-09 14:18:32 +08:00 |
|
|
|
bf7eee9d7b
|
[Bugfix][EC Connector] Fix ECExampleConnector load device under TP>1 (#40416)
Signed-off-by: Hang Gong <kidogong@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-09 11:44:30 +08:00 |
|
|
Qiming Zhang
|
27b63fb8f8
|
[CI][XPU] skip test_sampling_mask_tensors_match_finite_support on XPU (#55852)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-09-09 11:16:03 +08:00 |
|
|
Akine-Ko
|
41541636fd
|
[Refactor][EC Connector] Add backend extension points to ECCPUWorker (#54033)
Signed-off-by: Akine-Ko <2923601304@qq.com>
|
2026-09-08 20:13:47 -07:00 |
|
|
Tianyu GuoandOpenAI Codex
|
f1aeff6007
|
[Bugfix][EC Connector] Fail the request, not the engine, when a remote encoding cannot arrive (#55290)
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-08 20:13:33 -07:00 |
|
|
djramicandAndreas Karatzas
|
c6ba5e89d6
|
[Bugfix][Elastic EP] Route only to surviving engines during scale-down (#55772)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-08 21:28:28 -05:00 |
|
|
|
0b066293f3
|
[Core][KV Connector] Resolve connector block tables for every scheduled request (#54853)
Signed-off-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-09 02:15:53 +00:00 |
|
|
|
9c2d21046b
|
[Bugfix][Spec Decode] Honour the draft's moe_backend on Model Runner V2 (#54788)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-08 16:50:07 -07:00 |
|
|
Flora FengandWentao Ye
|
29f46ac475
|
[Perf] Eliminate full-history reasoning scans for structured outputs (#55223)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Signed-off-by: Flora Feng <4florafeng@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-09-08 14:07:16 -07:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
db3814a4f2
|
[Attention] Require explicit DCP support from attention implementations (#55780)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-08 14:04:27 -07:00 |
|
|
|
d29c88f162
|
[Core] Let SWA layers take the primary block size to avoid inflating the KV block LCM (#53007)
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-08 16:44:43 -04:00 |
|
|
|
e0aaef85f3
|
[2/N][KV Connector][NIXL] Support per-region transfer geometry (#53780)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-08 16:01:12 -04:00 |
|
|
Wentao Ye
|
07950d4734
|
[Kimi Bug] Fix kimi k3 startup cuda graph issue with recoverSSM (#55774)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-08 10:29:53 -04:00 |
|
|
|
263c4ff95f
|
[Bugfix][Spec Decode] Cache the Mamba state at the block-grid position of EAGLE resume (#53945)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Adam Shaver <ashaver@nvidia.com>
Signed-off-by: akshaver <168006157+akshaver@users.noreply.github.com>
Co-authored-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: roikoren755 <26850796+roikoren755@users.noreply.github.com>
|
2026-09-08 09:59:58 -04:00 |
|
|
Andy LoandOpenAI Codex
|
5ebce2391e
|
[Bugfix][KV Offload] Respect prefix-cache bypass in SimpleCPUOffload (#54998)
Signed-off-by: Andy Lo <andy@mistral.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-08 13:14:19 +00:00 |
|
|
ahmed xijiaat
|
81dabe2e5d
|
[Bugfix][KV Offload] Validate SWA coverage at unaligned cache-hit boundaries (#55712)
Signed-off-by: xijiade.aihemaiti <3146335281@qq.com>
|
2026-09-08 10:15:48 +03:00 |
|
|
He LiuandKimi
|
eb6b619ab2
|
[Bugfix][KV Offload] Register mixed page sizes in one cache group (#54756)
Signed-off-by: heliubj18 <chengfeng@ppio.com>
Co-authored-by: Kimi <noreply@moonshot.cn>
|
2026-09-07 20:50:15 -07:00 |
|
|
Wentao Ye
|
869f78732b
|
[Kimi Bug] Fix kimi k3 AssertionError assert 0 <= checkpoint_idx < len(blocks) (#55747)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-07 22:34:48 -04:00 |
|
|
Kevin H. LuuandCodex
|
58f09211dd
|
[CI] Synchronize shared offload unlink test before observing pathname (#55604)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-07 12:52:36 -07:00 |
|
|
|
42801b3a6b
|
[3/N][warmup][DSv4] Migrate FA4 MLA and shared CuTeDSL kernels (#53565)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-07 09:36:35 -04:00 |
|
|
Kam BasraandClaude
|
4a806d08ee
|
[Bugfix] OffloadingConnector: stop zeroing offload hits under MTP/EAGLE spec decode (#52771)
Signed-off-by: Kam Basra <kameldipbasra@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-09-07 15:16:05 +03:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
e476556189
|
[ROCm][CI] Add attention-sink support to ROCm AITER sparse MLA (#54404)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-07 09:26:47 +00:00 |
|
|
Zhewen Liandzhewenl
|
34b1e9f7a6
|
[Bugfix][MooncakeStore] Fix finish-time save crash on hybrid models (#54643)
Signed-off-by: zhewenl <zhewenl@users.noreply.github.com>
Co-authored-by: zhewenl <zhewenl@users.noreply.github.com>
|
2026-09-07 07:18:30 +00:00 |
|
|
|
6fbb00b188
|
[EPD] Add ECMooncakeConnector for encoder cache over Mooncake TransferEngine (#41567)
Signed-off-by: Teng Ma <sima.mt@alibaba-inc.com>
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
Signed-off-by: Zhou ziheng <jiaranran2@gmail.com>
Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Tianyu Guo <guoty@inferact.ai>
Co-authored-by: Zhou ziheng <jiaranran2@gmail.com>
Co-authored-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-07 06:21:43 +00:00 |
|
|
Wei Zhao
|
c3ec0d29f5
|
[Bugfix] Fix cuda profiler missing bug (#55237)
|
2026-09-07 03:15:57 +00:00 |
|