|
4bac767695
|
[Perf][Nemotron] Skip redundant latent-MoE all-reduce at TP>1 (~13% decode win) (#52301)
Signed-off-by: Junhao Shen <junshen@nvidia.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-15 07:33:51 -07:00 |
|
|
aoshen02
|
eb61707851
|
[Bugfix] Fix stale HPC QK-norm weights after weight refit (#56706)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
|
2026-09-14 21:34:41 -07:00 |
|
|
|
9d14fd3095
|
[Kernel][MoE] DeepEP v2: async finalize to overlap shared experts with combine (#52781)
Signed-off-by: Mario <404mario@users.noreply.github.com>
Co-authored-by: Mario <404mario@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-09-15 00:04:22 -04:00 |
|
|
Fangzhou AiandCursor
|
00972dfd72
|
[ROCm][DSV4.1][Perf] Fold the mHC post step into the delayed pre projection (#56513)
Signed-off-by: Fangzhou Ai <fangzhou@semianalysis.ai>
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-14 16:44:56 -05:00 |
|
|
|
03dc26e639
|
[Perf][Kernel][Quantization] Fuse ReLU2 with static FP8 activation quantization (#53793)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: snordmann <snordmann@nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-14 10:26:15 -07:00 |
|
|
Ronald
|
e0c04c7b4d
|
[Bugfix][Models] Fix OpenPangu sleep mode with static sinks (#53696)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
|
2026-09-14 21:05:47 +08:00 |
|
|
|
238cb2b191
|
[Perf][GLM-5.3-Flash] Dense/masked-MHA sparse prefill for the NoPE (256, 0, 256) layout + skip the NoPE K concat (#55738)
Signed-off-by: Jared Wen <jaredwen@inferact.ai>
Signed-off-by: Jared Wen <w13431838023@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-14 09:36:39 +00:00 |
|
|
Li, Jiang
|
79f0be21ff
|
[Bugfix][CPU] Fix DeepSeek-R1 (FP8 MLA + MoE) correctness on CPU backend (#56773)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-09-14 17:30:28 +08:00 |
|
|
|
78e84261ab
|
[Performance] Add Triton kernel for Gemma3n sparse GELU (#48498)
Signed-off-by: BWAAEEEK <jooho414@gmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-09-14 07:42:15 +00:00 |
|
|
Bugen Zhao
|
cf1584f373
|
[Refactor] Normalize DeepSeek V4.1 model package naming (#56741)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-13 23:17:50 -07:00 |
|
|
|
b7e0cdac5d
|
[Bugfix] Detect unloaded NVFP4 weight scales with a NaN sentinel (#52501)
Signed-off-by: pavelzak <pavel.zakharov@gmail.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-13 14:58:09 +00:00 |
|
|
|
fa008bdccf
|
[Perf][Kernel] Integrate DeepSelect TopK for the DSA sparse indexer (#56464)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-09-13 00:44:37 -07:00 |
|
|
|
aed894c190
|
[6/N][warmup][DSv4] Migrate sampling, and DFlash JIT kernels (#56323)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-12 17:24:24 -07:00 |
|
|
|
ebe1dec2da
|
[PCP][DCP] Enable PCP+DCP on sparse-MLA models (#56157)
Signed-off-by: patryk.saffer <patryk.saffer@blc-login-1.blc1.mistralcompute.ai>
Signed-off-by: patryk.saffer <patryk.saffer@blc-login-0.blc1.mistralcompute.ai>
Signed-off-by: PatrykSaffer <patryk.saffer@mistral.ai>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: patryk.saffer <patryk.saffer@blc-login-1.blc1.mistralcompute.ai>
Co-authored-by: patryk.saffer <patryk.saffer@blc-login-0.blc1.mistralcompute.ai>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Patryk Saffer <PatrykSaffer@users.noreply.github.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-12 23:24:44 +00:00 |
|
|
Itay Alroy
|
658c8131c7
|
[Elastic EP] Reuse CUDA graphs across reconfiguration (#54985)
|
2026-09-12 10:26:39 -04:00 |
|
|
JartX
|
986e2f870a
|
[Refactor][ROCm] Migrate the RDNA3 W4A16 MoE to the oracle/experts pa… (#55522)
Signed-off-by: JartX <sagformas@epdcenter.es>
|
2026-09-12 21:20:26 +08:00 |
|
|
|
d43bb2f37f
|
[3/N] HiSparse: host-resident sparse-MLA decode hot-buffering (#53781)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Matthew Bonanni <matthew@neuralmagic.com>
Signed-off-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@mistral.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-09-12 00:36:47 -04:00 |
|
|
Fangzhou AiandFangzhou Ai
|
46d2b23ac5
|
[ROCm][DSV4.1][Perf] Use AITER mHC for the delayed pre block (#56503)
Signed-off-by: Fangzhou Ai <fangzhou@semianalysis.ai>
Co-authored-by: Fangzhou Ai <fangzhou@semianalysis.ai>
|
2026-09-12 00:35:48 +00:00 |
|
|
Andy Lo
|
dc07f1638f
|
[Bugfix][MLA] Read sparse model settings from text config (#56160)
Signed-off-by: Andy Lo <andy@mistral.ai>
|
2026-09-11 18:02:13 +00:00 |
|
|
|
6fe67cbbf3
|
[Spec][V2] Support MTP speculative decoding under pipeline parallelism (#46994)
Signed-off-by: Chris Eastwood <chris.eastwood@pwn4g3.dev>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-11 17:55:21 +00:00 |
|
|
Shanshan Shen
|
127143e27f
|
Revert "[Rocm][Kimi-k3] Fix pipeline_parallel support for the kimik3 DCP mode (#53664)" (#56429)
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
|
2026-09-11 09:17:26 -07:00 |
|
|
Wentao Ye
|
5fe77aecfc
|
[Deprecation] Deprecate items scheduled for 0.29 (#55353)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-11 08:17:02 -07:00 |
|
|
Harry MellorandClaude Opus 5
|
c191787a68
|
[Bugfix] Align vLLM YaRN with Transformers and stop re-scaling max_model_len (#56446)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-11 13:01:38 +00:00 |
|
|
Matt
|
b4da4d17ae
|
[ROCm][Bugfix] Fix AITER preshuffled FP8 block-scale kernel (#56433)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
|
2026-09-11 11:44:57 +00:00 |
|
|
|
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 |
|
|
|
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 |
|
|
Marceli FylcekandClaude Opus 5
|
5b6cf93e8e
|
[XPU] Add forward_xpu to Mixer2RMSNormGated and FusedRMSNormGated (#54968)
Signed-off-by: Marceli Fylcek <marceli.fylcek@intel.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-11 07:58:28 +08:00 |
|
|
MattandClaude Opus 5
|
9163190dda
|
[ROCm][Bugfix][Perf] Tune multi-stream shared experts use; wvSplitKrc fixes (#56098)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-10 15:14:22 -07:00 |
|
|
Micah Williamson
|
7de70fa7ae
|
[Bugfix][ROCm] Create linear layer biases with requires_grad=False (#56161)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-09-10 13:54:52 -05:00 |
|
|
Itay AlroyandTyler Michael Smith
|
bdea2777ea
|
[Bugfix][MoE] Fix batched CUTLASS workspace overallocation (#55579)
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-09-10 15:33:56 +00:00 |
|
|
siyuandIsotr0py
|
73fb19151f
|
[Fast Start] Support fp4 (#55465)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-10 13:22:17 +00:00 |
|
|
|
9b959b8657
|
[Model] DeepSeek-V4.1-Flash Model Definitions (#56228)
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-10 20:16:26 +08:00 |
|
|
Jakub ByczkowskiandCopilot
|
c9355e25e8
|
[XPU][Bugfix] Add forward_xpu to Ernie4_5_VLRotaryEmbedding (#55942)
Signed-off-by: Jakub Byczkowski <jakub.byczkowski@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
|
2026-09-10 17:48:00 +08:00 |
|
|
|
fe26c705f7
|
[Model] Add Bailing V3 VL support (#55921)
Signed-off-by: zexplorerhj <zhjoneson@163.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-10 02:46:56 -07:00 |
|
|
Jared WenandClaude Fable 5.1
|
1768273c13
|
[Perf][GLM-5.3-Flash] Decode hot-path cleanups: strided KDA recurrent inputs, NoPE MQA query without concat, no duplicate router GEMM (#55736)
Signed-off-by: Jared Wen <jaredwen@inferact.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-10 16:28:33 +08:00 |
|
|
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 |
|
|
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 |
|
|
|
d8d53f17c2
|
[Rocm][Kimi-k3] Add pipeline_parallel support for the kimik3 model (#53664)
Signed-off-by: haic0 <149741444+haic0@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-09 07:50:24 -07:00 |
|
|
|
cc4210f671
|
[Perf] Improve BF16x3 router GEMM accuracy and make it default on sm100 (#55899)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-09 07:33:12 -07:00 |
|
|
Harry Huangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
3116c5d06b
|
[Qwen4Exp] Support UVA PLE-offload and Engram tensor parallelism (#54371)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-09 07:32:34 -07:00 |
|
|
|
60ad959b6f
|
Fix block FP8 MTP in ModelOpt mixed checkpoints (#55513)
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-08 22:47:21 +00:00 |
|
|
|
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 |
|
|
Roderick Wuandmgoin
|
2c9d68f80b
|
[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)
Signed-off-by: Roderick-Wu <roderickwu2003@gmail.com>
Signed-off-by: Roderick Wu <roderickwu2003@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-08 12:45:12 -07:00 |
|
|
|
8ebc5b0a18
|
[Bugfix] Fix NVFP4 fused SiLU+mul scale allocation and global scale direction (#55643)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: khluu <khluu000@gmail.com>
Co-authored-by: jiahao <jxia77@terpmail.umd.edu>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
|
2026-09-08 08:26:07 -07:00 |
|
|
Wentao Ye
|
6b15bea080
|
[Refactor] Remove utils dead code (#53941)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-08 11:22:09 -04:00 |
|
|
Canlin GuoandOpenAI Codex
|
8e1f97e709
|
[Qwen3.8-Flash-Next] Tune FP8 TP2/TP4 Triton MoE on B200 (#55890)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-08 22:45:18 +08:00 |
|
|
Stefano Castagnetta
|
f6326f53bd
|
[Perf][GDN] Enable the FlashInfer GDN prefill kernel on SM12x (#55715)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
|
2026-09-08 12:26:03 +00:00 |
|