|
560ef78bfe
|
[Perf][Model Runner V2] Compact sampling masks on GPU instead of unpacking the full-vocab bitmask on CPU (#54901)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: vx120 <893600387@qq.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: vx120 <893600387@qq.com>
|
2026-09-03 19:03:36 -07:00 |
|
|
Jiangyun Zhu
|
98ed0856f3
|
[Model] add GLM-5.3-Flash support (#53906)
|
2026-09-03 09:40:35 -07:00 |
|
|
Giancarlo Delfin
|
facd9a74a1
|
[Model Runner V2][Spec Decode] Skip DP sync for all speculator uniform decodes (#54856)
|
2026-09-03 10:32:33 +00:00 |
|
|
Isotr0py
|
1c26e57d3c
|
[Bugfix] Raise for unavailable piecewise CUDA graphs (#54782)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-02 08:52:24 +00:00 |
|
|
Andrii SkliarandAndrii Skliar
|
adebc41b7e
|
[Mamba] Add FlashInfer ReplaySSM backend (#52506)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Signed-off-by: Andrii Skliar <andreyws96@gmail.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
|
2026-09-01 10:26:43 -04:00 |
|
|
Roberto L. CastroandCodex
|
e16b5e518d
|
[1/N][warmup][DSv4] Migrate generic MLA metadata and indexing kernels (#50175)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-08-31 23:26:05 -04:00 |
|
|
Nick Hill
|
c28feab989
|
[Core][MRV2] Freeze gc during V2 CG capture; skip per-descriptor cleanup (#54646)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-31 19:37:46 -07:00 |
|
|
AusarandClaude
|
6bafc049aa
|
[Bugfix][PP] Never drop a decoding request from the sampled-token broadcast (#54436)
Signed-off-by: ArcheyChen <45146080+ArcheyChen@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-31 23:49:54 +00:00 |
|
|
Zihan ZhangandClaude Opus 5
|
d61b6e1878
|
[Bugfix][Spec Decode] Take the DFlash draft's RoPE layout from its own config (#54373)
Signed-off-by: SubSir <tiancaizhangdaxian@sjtu.edu.cn>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-08-31 18:13:20 -04:00 |
|
|
Artem Perevedentsev
|
39e276eaeb
|
[Structured Output] Let terminal grammars stop under min_tokens (II) (#54218)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-08-31 20:39:27 +04:00 |
|
|
+5
|
e126687a9a
|
[Model] Support Qwen3.8-Flash-Next (#53896)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
Signed-off-by: andyluo7 <andy.luo@amd.com>
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: Harry Huang <huanghaoyan.hhy@alibaba-inc.com>
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: KungYork <firelikest@163.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: andyluo7 <43718156+andyluo7@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-31 05:57:56 +00:00 |
|
|
Canlin Guoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
b383e16396
|
[Bugfix] Reset cached Mamba align metadata on profiling teardown (#54044)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-30 00:43:20 -07:00 |
|
|
Giancarlo Delfin
|
fe755c8899
|
[Bugfix][Model Runner V2][Spec Decode] Decouple the draft's gumbel noise stream from the target's (#54282)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
|
2026-08-29 09:58:29 -07:00 |
|
|
Nicolò Lucchesi
|
7f4793eaa3
|
[Nixl][PD] DCP support for MLA models (#50611)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
|
2026-08-29 16:03:53 +00:00 |
|
|
|
d3d79ffc1e
|
[Bugfix][Spec Decode] Capture the widest uniform decode batch by default (#50488)
Signed-off-by: Rahul Chalamala <22563365+rchalamala@users.noreply.github.com>
Signed-off-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Signed-off-by: Rahul Chalamala <rahul@modal.com>
Co-authored-by: Janelle Cai <janelle.cai@modal.com>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Devin <devin@cognition.ai>
|
2026-08-28 22:38:13 -07:00 |
|
|
Summer Yang
|
6d4562c59b
|
[Attention][DCP] Enable FlashInfer MLA for DSpark drafting (#54277)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
|
2026-08-28 21:11:28 -07:00 |
|
|
|
b2f685834a
|
[Hy4] support Hy4-preview model (#54160)
Signed-off-by: chengvjiang <chengvjiang@tencent.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: chengvjiang <chengvjiang@tencent.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: russellfeng <russellfeng@tencent.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-29 12:07:28 +08:00 |
|
|
Nick Hill
|
6c18a54648
|
[Perf] Avoid h2d copies from non-pinned CPU tensors (#54299)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-29 12:06:30 +08:00 |
|
|
Summer YangandNick Hill
|
2aac565cae
|
[Core][KV Connector] Start async KV loads after the forward launch when no sync loads are scheduled (#53333)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-28 21:58:00 +00:00 |
|
|
Nick HillandKimi Code
|
96242aa50d
|
[Bugfix][MRV2] Release layer-bound KV cache memory in shutdown() (#54246)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
|
2026-08-28 21:27:09 +00:00 |
|
|
Ronaldandaoshen02
|
479eeb32d2
|
[Bugfix][MRV2] Isolate sleep-mode KV allocations (#53508)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-08-27 15:08:28 -07:00 |
|
|
Qiu Chunshuo
|
b3af042abd
|
Bugfix: use PCP slot mappings for PIECEWISE capture (#53869)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
|
2026-08-27 05:39:36 +00:00 |
|
|
Giancarlo Delfin
|
5acc1c4e4b
|
[Model Runner V2][Spec Decode] Skip DP sync before EAGLE/MTP draft prefill (#53694)
|
2026-08-26 20:59:35 -07:00 |
|
|
Wei Zhao
|
94d96e2446
|
[Bugfix] Release CUDA graph profiling memory before KV cache allocation (#53955)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-27 01:35:59 +00:00 |
|
|
fanxingran
|
080a66a69c
|
[Bugfix][ROCm] Capture CUDA graphs on the current stream (#53818)
Signed-off-by: fanxingran <xingran.fan@amd.com>
|
2026-08-26 23:16:45 +08:00 |
|
|
|
b1fbbc2ade
|
BugFix(PCP): use persistent input buffers for PIECEWISE CUDA graphs (#53515)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-26 05:58:13 +00:00 |
|
|
Wentao Ye
|
a447955aca
|
[Kimi Bug] Fix k3 torch.AcceleratorError: CUDA error: an illegal memory access was encountered (#53773)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-25 17:38:48 -07:00 |
|
|
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 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 |
|
|
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 |
|
|
|
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 |
|
|
|
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 |
|
|
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 |
|
|
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 |
|
|
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 |
|
|
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 |
|
|
|
a4d70bef37
|
[Model Runner V2] Reserve CUDA graph memory (#53306)
Signed-off-by: Anh Tran <anh.tran.3889@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Anh Tran <anh.tran.3889@gmail.com>
Co-authored-by: anhtra3889 <anhtra@nvidia.com>
|
2026-08-23 23:11:19 -07:00 |
|
|
Zhou248
|
2f55ef254c
|
[Model] Add Qwen3-Omni DSpark support (#52560)
Signed-off-by: Zhou248 <630563665@qq.com>
|
2026-08-22 15:35:22 -07:00 |
|
|
|
da329cc303
|
[Bugfix] Fix speculative decoding for short_conv (LFM2) models (#50272)
Signed-off-by: jens.luecke <jens.luecke@liquid.ai>
Co-authored-by: Tonoken3 <sakamakismile@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-22 13:34:22 +00:00 |
|
|
Tianyu Guo
|
7ca49fbe4b
|
[Refactor][Model Runner V2][Multimodal] Move the encoder-only path out of the shared runner (#53176)
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
|
2026-08-22 05:11:44 +00:00 |
|
|
Lucas Wilkinson
|
8bdc70ec7b
|
[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-08-21 17:47:49 -07:00 |
|
|
Misha Goin
|
9ff7041b55
|
[Bugfix][Spec Decode] Use group geometry for FlashAttention metadata (#53002)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-08-21 17:07:19 -07:00 |
|
|
Zihan Zhang
|
b389ac2946
|
[Spec Decode] DFlash2: local convolution + candidate selector (#52816)
|
2026-08-20 22:27:22 -07:00 |
|
|
|
91a893de64
|
[Bugfix][Spec Decode] Scope DSpark backend inheritance to DeepSeek V4 (#52809)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-20 18:42:08 -07:00 |
|
|
|
01af92e175
|
[Feature][Model Runner V2] Support extract_hidden_states speculation (#49811)
Signed-off-by: Zupeng Wang <71580390+zupengwang@users.noreply.github.com>
Signed-off-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: OpenAI <support@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-20 11:13:43 -04:00 |
|
|
|
a1c5b1fd9f
|
[Core][V1] Support trace_decode_token_ids for deterministic decode replay (#46701)
Signed-off-by: ianzxliu <ianzxliu@tencent.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: Zhixia Liu <liuzhixia.nju@gmail.com>
Co-authored-by: ianzxliu <ianzxliu@tencent.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-20 15:12:43 +08:00 |
|
|
Giancarlo Delfin
|
d4f4d3f40f
|
[Model Runner V2][Spec Decode] Fix draft logits cache column stride in gumbel_sample (#53017)
|
2026-08-19 17:39:30 -07:00 |
|
|
Roger Wang
|
755492e37d
|
Revert "[Kernel] Gemma-4 FA4 FP8 Kernel" (#52987)
|
2026-08-19 10:48:46 -07:00 |
|
|
Itay Alroy
|
a2257f95b7
|
[Elastic EP] Reduce eager-mode reconfiguration downtime (#51885)
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
|
2026-08-19 02:13:06 +00:00 |
|