613 Commits
Author SHA1 Message Date
7c9042c05a [Bugfix][MRV2] Fix speculative warmup deadlock with pipeline parallelism (#62129)
Signed-off-by: chenjr97 <chenjr97@mail2.sysu.edu.cn>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
2026-10-17 23:51:32 -07:00
Nick HillandClaude Opus 5.5 0c5dd18e7a [MRV2] Collect KV transfer results before the drafter runs (#62041)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-17 10:27:57 -07:00
61bb590877 [Bugfix][Spec Decode] Clear stale shared block-table rows (#61174)
Signed-off-by: Cheng Rui <286040359@qq.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
2026-10-17 01:25:02 -07:00
c3de0b37e2 [Core][Spec Decode] Replace EAGLE group heuristics with explicit draft-layer tags (#61455)
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-17 08:22:33 +00:00
7b6310c109 [Perf][Sampler] Speed up the small-batch split top-p pipeline (#61996)
Signed-off-by: Bowen Wang <bowen@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: vllm-agent <claw@inferact.ai>
2026-10-16 21:22:11 -07:00
b544587408 [Core][Feat] Pluggable KVCacheConfigBuilder for platform/model-specific KV cache planning (#53558)
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
2026-10-16 23:16:47 +00:00
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
de7d70676d [Perf] Low-latency CPU all-reduce for DP metadata syncs (#61767)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: hjjq <50634613+hjjq@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-15 15:29:13 -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
d12ea8e309 [Bugfix][MRV2] Keep input_ids on later PP stages for raw-token models (#61016)
Signed-off-by: booth-algo <kevinlauofficial01@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-10-15 12:54:21 -07:00
FeanorandTaneem Ibrahim 5d5c3d7c43 [Bugfix] Preserve padding token types for cross encoders (#58143)
Signed-off-by: zhaoye <772971548@qq.com>
Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
2026-10-15 03:09:24 +00:00
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
Ayushman Singh 9b5c6707a3 [Bugfix][MRV2] Capture DCP FULL cudagraphs with KV context (#61496)
Signed-off-by: Ayushman Singh <40520701+ayush1399@users.noreply.github.com>
2026-10-14 19:20:48 +00:00
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
857ddac4e5 [Perf][MRV2] Skip empty draft-token resets on request admission (#61640)
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-10-14 12:01:01 -07:00
qizixiClaude Opus 5.5mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
c1407a7e86 [Spec Decode][MRV2] Warm up top-k/top-p and greedy rejection kernels for speculative decoding (#59260)
Signed-off-by: zixi-qi <zixi@inferact.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>
2026-10-14 14:59:21 -04:00
Almog TavorandItay Alroy 87e7dce3a7 [MRV2] Keep warmup out of the EPLB load stats (#56716)
Signed-off-by: almogtavor <almogtavor@gmail.com>
Co-authored-by: Itay Alroy <75032521+itayalroy@users.noreply.github.com>
2026-10-14 00:00:48 +00:00
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
df6c7ad031 [Core][Refactor] Move KV cache planning logic to kv_cache_planning.py (#61183)
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-13 03:05:39 +00:00
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
Woosuk KwonandClaude Opus 5.5 e1a5086256 [Attention] Remove cascade attention (#61126)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 10:41:07 -07:00
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
Yan Ma f147949be8 [XPU] limit FA kernel block size to multipleOf 64 (#57297)
Signed-off-by: Yan Ma <yan.ma@intel.com>
2026-10-12 10:25:32 +08:00
dingdangmaoandCodex 124b89d5b7 [Bugfix][RecoverSSM] Correct aligned state indices at exact block boundaries (#59962)
Signed-off-by: apex-mochen <2756823972@qq.com>
Co-authored-by: Codex <noreply@openai.com>
2026-10-12 02:08:14 +00:00
Nick Hill 3fe917abb1 [Bugfix][MRV2] Fix FlashInfer attention and ReplaySSM warmups on MRV2 (#61013)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-10-11 16:04:41 -07:00
Nick Hill f8471164bf [MRV2] Detatch weight-reload logic from MRV1 (#60937) 2026-10-10 21:15:05 -07:00
f2376cdc4d [Fast Start] Preload the FlashInfer autotune table on the weight cache daemon (#60085)
Signed-off-by: liusy58 <mg21330037@smail.nju.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
2026-10-10 15:48:06 +00:00
Matthew BonanniandClaude Opus 5.5 d5f356dae0 [HiSparse] Own GPU residency instead of editing core block-table rows (#60647)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-09 21:25:44 -07:00
DimensionSTPandOpenAI Codex 10cc2f6ae2 [Bugfix] Bound GDN speculative decode query widths (#55504)
Signed-off-by: DimensionSTP <65501090+DimensionSTP@users.noreply.github.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-10-10 11:00:16 +08:00
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
zzaebokandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 702ce313f4 [Perf][Multimodal] Sort multimodal encoder inputs by modality (#60196)
Signed-off-by: Jaebok Lee <jaebok9541@naver.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-09 10:55:36 +08:00
Mia OjedaandLucas Wilkinson 4611c2c3d2 [BugFix][DiffusionGemma][CPU] Copy async output snapshots instead of aliasing reused buffers (#59829)
Signed-off-by: ojeda-e <eojeda@league.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-10-08 19:16:51 -07:00
Woosuk Kwon 194bd72be7 [Compile] Remove torch.compile-based sequence parallelism and AsyncTP (#60517) 2026-10-08 08:28:23 -07:00
fd928e5f3c [Bugfix] Check batch-invariance support for every attention backend (#60271)
Signed-off-by: yifanFengg <evanfengff@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2026-10-08 11:19:57 -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
3d6853b32c [Bugfix] Seed hybrid mamba state index with mamba_block_size on prefix-cache hits (#55601)
Signed-off-by: pondzikk <pondzik@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>
Co-authored-by: ptorsten <1652174+ptorsten@users.noreply.github.com>
2026-10-07 17:09:50 +00:00
8a26869bca [Bugfix] Index Mamba align state copies by request slot in MRV2 (#60210)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Karl0007 <44745209+Karl0007@users.noreply.github.com>
Co-authored-by: Yongqin Wang <yongqinwang@roblox.com>
2026-10-07 02:32:46 +00:00
956960f85f [Perf][MRV2] Avoid stream syncs in NonUvaBuffer host-to-device copies (#60215)
Signed-off-by: cheesecake <farzanaman99@gmail.com>
Co-authored-by: William Joyner <133391209+joynerwk03@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-07 01:51:12 +00:00
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
Juntian LiuClaude Opus 5.5mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
eb2901b735 [Perf][DSv4.1] Run decoder replay layers in CUDA graphs and trim in PIECEWISE graphs (#59532)
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-05 22:11:45 -07:00
Vadim GimpelsonCursor Agentmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
0eac152707 [Bugfix] Route every speculation-capable row through the speculative path so recurrent state stays consistent (#56531)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-10-06 03:03:44 +04:00