208 Commits
Author SHA1 Message Date
cjackal 663e535640 [Perf][Spec Decode] Skip bonus-logit reduction for short drafts in rejection sampling (#61451)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
2026-10-16 12:42:48 -07:00
Stefano CastagnettaandKevin H. Luu 784d1fff0c [MRV2][Spec Decode] Quantized draft lm_head for drafters that share the target head (#59973)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 22:06:40 +00:00
d92a4f25f2 [watermarking] Add DFlash support to dual-key gumbel-max watermarking (#59554)
Signed-off-by: Shern Shiou Tan <shernshiou@gmail.com>
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Raphael Rialland <raphael.rialland@mistral.ai>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-10-15 22:06:06 +00:00
DimensionSTPandKevin H. Luu 9edcc7fa7e [Bugfix][Spec Decode] Avoid reusing random draws across block verification rounds (#61161)
Signed-off-by: DimensionSTP <65501090+DimensionSTP@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 14:46:38 -07:00
bfdbfa1632 [Bugfix][PCP] Align MoE routing padding with gathered tokens (#60946)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: wangyicong <wangyicong@bytedance.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-10-14 21:04:00 -04:00
Juntian LiuandClaude Opus 5.5 388a610dfb [Perf][DFlash] Capture context combine and anchor in the draft CUDA graph (#59511)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-14 15:40:52 -04:00
Sandeep AgrawalandKevin H. Luu 21e207efa1 [Bugfix][MRV2][Spec Decode] Honor EAGLE3 single-state draft configuration (#61563)
Signed-off-by: Sandeep Agrawal <sandeepa@nvidia.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-14 12:09:06 -07:00
Chaunceyandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> ad8d39cbab [Bugfix] Fix DSpark graph-padding handling in the DeepSeek-V4.1 MoE fused top-k (#59166)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-14 07:49:52 +08:00
Wentao Ye d0948f754d [Bug] Honor spec decode draft model config (#61240)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-10-12 15:13:23 -04:00
Ilya Markov a281ad32f0 [EPLB] Add EPLB support to dspark draft models (DeepSeekV4) (#57549)
Signed-off-by: Markov Ilya <markovilya197@gmail.com>
2026-10-12 10:03:09 -04:00
Chauncey ac28877f0e [Bugfix] Fix out-of-bounds lookahead in adaptive block verification (#60945)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-10-12 09:21:35 -04:00
Giancarlo DelfinandRishi Puri 36f3972812 [Spec Decode] Skip metadata build for dflash/dspark when all model backends support it (#60692)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Rishi Puri <20074092+puririshi98@users.noreply.github.com>
2026-10-12 00:09:10 -07:00
Nick Hill 7d1d8660d6 [MRV2] Miscellaneous code structure updates (#60754)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-10-09 17:58:09 -07:00
ed7ae705a1 [Bugfix][MRV2] Use int64 index mappings to fix row-offset overflow (#60736)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-09 14:38:11 -07:00
02e55d2af3 [KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-10-09 15:48:37 -04:00
Giancarlo Delfin 6ee9be6b3c [Spec Decode] Rename AR speculators to StandaloneAR / TargetDependentAR (#60335)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
2026-10-07 14:01:59 -04:00
Cheese CakeandClaude Opus 5.5 b6d8e8afd9 [Bugfix][MRV2][Spec Decode] Accept num_speculative_tokens in NgramGPUSpeculator.propose (#60300)
Signed-off-by: cheesecake <farzanaman99@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 15:02:04 -07:00
819852df6b [ModelRunner V2] Speculative Decoding NGram GPU Implementations (#40704)
Signed-off-by: PatchouliTaisa <patchychen@tencent.com>
Signed-off-by: PatchouliTaisa <pyramkar@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Xuanan Chen <xuananchenc@nvidia.com>
Co-authored-by: PatchouliTaisa <patchychen@tencent.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Xuanan Chen <xuananchenc@nvidia.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
2026-10-06 13:32:59 -07:00
Giancarlo Delfin fcf53d240c [Spec Decode] Remove eager metadata rebuild during MTP fused multi-step decode (#58463)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
2026-10-06 12:17:30 -04:00
Wentao Ye 74c5cbcd7b [Bugfix][MRV2][Spec Decode] Honor dynamic K in autoregressive speculators, 1.2~1.3x kernel perf improvement (#57053)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-10-05 14:54:11 -04:00
Wentao Ye 8bdd8d847d [GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (#57443)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-10-02 20:05:27 -04:00
4056c8ac1f [Bugfix][HiSparse] Fix MTP acceptance collapse under FULL graphs with a saturated GPU pool (#59309)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
2026-10-01 23:04:21 -07:00
c4fc3c7d32 [Bugfix][Spec Decode] Per-module LM heads for multi-layer MTP on Model Runner V2 (#58921)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: chanh <channguyen@nvidia.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-01 01:09:14 -07:00
70be6aae19 [Feature][Spec Decode] Support sampling mask replay for MRV2 MTP (#59359)
Signed-off-by: Cuiping Cheng <chengcuipingswu@163.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Cuiping Cheng <chengcuipingswu@163.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-01 13:51:39 +08:00
34c458d27f [Bugfix] Don't let a structured-output request sample from an unmasked row (#54442)
Signed-off-by: ArcheyChen <45146080+ArcheyChen@users.noreply.github.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: GPT-5.6 <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2026-10-01 02:11:44 +00:00
0f8b398158 [watermarking] add context deduplication support to speculative decoding (#56807)
Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai>
Signed-off-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Simon Veitner <sveitner@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-09-30 12:22:10 -04:00
Giancarlo DelfinandWoosuk Kwon 3d5f4d4cd5 [Perf][Spec Decode] Avoid triton recompiles in the acceptance estimator (#57107)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
2026-09-28 13:46:25 -07:00
fedbc3b564 [Bugfix][MRV2][Spec Decode] Reject draft slots that were never proposed (#58784)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-09-28 13:07:15 -07:00
Nick HillNicolò LucchesiClaude Opus 5.5mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Yongye Zhu
e7c903609f [Perf][MRV2] Allow FULL decode graphs for one-token prompt tails (#58400)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
2026-09-28 12:48:52 -07:00
Xiaoshuang Wangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> ef42093a36 [Model Runner V2][Spec Decode] Support spec decode with draft model (#43091)
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-28 19:38:05 +00:00
927c87b347 [PCP][DCP] Support DCP target model with non-DCP Dspark (#56723)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-26 18:12:35 -04:00
a4eb3f25d6 [Spec Decode] Enable Gemma4 DSpark adaptive verification with FlashInfer (#57263)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-09-26 17:01:17 +08:00
73a78e6f1f [SpecDecode] Add LiLiCorr drafter (#57934)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: Andrii Skliar <andreyws96@gmail.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
2026-09-25 10:08:28 -04:00
Juntian LiuandClaude Opus 5.5 04730e8270 [DFlash] Capture the context K/V precompute in the draft CUDA graph (#57632)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-09-24 21:38:04 +00:00
Nick Hill 09fe178dba Revert "[DSpark] Support pipeline-parallel targets in aggregated serving (#56956)" (#58484) 2026-09-24 08:48:36 -07:00
Andreas KaratzasandOpenAI Codex 23110a0c9e [Bugfix] Capture prefill kernels for mixed FULL graphs (#58275)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-24 02:05:07 -07:00
Jhao-Ting Chen 4fb767ff0a [Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
2026-09-23 20:29:06 -07:00
Lucas WilkinsonQiuChunshuoClaude Fable 5.1CodexRobert ShawNick Hillmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
e6dc16cebd [PCP] Support prefill context parallelism with data parallelism (#57075)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-23 22:32:36 -04:00
157bcb7c48 [DSpark] Support pipeline-parallel targets in aggregated serving (#56956)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
2026-09-23 04:52:28 -07:00
Nick Hill afec265bca [MRV2] Miscellaneous code cleanup (#57980) 2026-09-23 01:51:52 -07:00
Lucas WilkinsonandClaude Fable 5.1 5c121e962a [SpecDecode] Restore residual-logits comments in _resample_kernel (#58166)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-22 08:07:31 -07:00
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
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
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
Yifan QiaoandClaude Fable 5.1 d2983f2f16 [Bugfix][Spec Decode] Stop dummy draft decode steps from writing KV through stale block-table rows (#56734)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-21 01:06:25 +00:00
5302d1fe40 [Model Runner V2] Support custom logits processors (#56497)
Signed-off-by: David Cheung <d7cheung@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-09-19 17:46:49 +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
Nick Hill f2aad6aa70 [MRV2] Buffer util simplifications (#56888)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-09-15 20:36:51 +00:00
zack 0136df94b0 [Bugfix][Spec Decode][MoE] Avoid uninitialized EPLB state in DeepSeek V4.1 DSpark drafter (#56387)
Signed-off-by: zack <51604064+luoyuctl@users.noreply.github.com>
2026-09-15 14:35:47 +00:00