 Rebecca LeeandCursor
|
6ca2b23e22
|
[ROCm] Expose kFp8DynamicTokenSym on AITER PTPC linears (#54248)
Signed-off-by: Rebecca Lee <rebecca.lee@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-16 11:48:30 -05:00 |
|
|
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 |
|
|
|
e97ff80613
|
[BugFix][PCP] Handle missing DP metadata in one-sided EP (#54016)
Signed-off-by: LopezCastroRoberto <robertol.c510@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-16 10:24:59 -04:00 |
|
|
linitra24
|
ca542ee154
|
[Model][LoRA] Enable LoRA support for ModernBertModel (#57148)
Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>
|
2026-09-16 14:16:09 +00:00 |
|
|
linitra24andJee Jee Li
|
c81eb3e69c
|
[LoRA] Support modules_to_save for sequence classification (#53555)
Signed-off-by: linitra24 <Joy25810@foxmail.com>
Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-16 07:15:42 -07:00 |
|
|
|
ec4a3a5370
|
[CI] Bump Transformers version to 5.17.0 (#56108)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-16 06:34:16 -07:00 |
|
|
|
975dca5bb5
|
[Perf][GDN] Scatter mixed speculative outputs into the caller buffer (#57140)
Signed-off-by: Arpan Tripathi <tripathiarpan20@gmail.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Xavier Lyu <9938360+xavierlyu@users.noreply.github.com>
Co-authored-by: Bohdan Podziubanchuk <114604629+Danbog32@users.noreply.github.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-16 13:03:57 +00:00 |
|
|
Harshit KediaandClaude Opus 5
|
6a2fdf9ac6
|
[Model] Optimize Sarvam MLA routing and preserve FP32 router logits (#56034)
Signed-off-by: Harshit Kedia <harshit@sarvam.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-16 20:02:47 +08:00 |
|
|
Adababyandshaolila
|
ceb87de065
|
[Misc] Remove no-op self-assignments across vLLM (#55988)
Signed-off-by: shaolila <shaolila@buaa.edu.cn>
Co-authored-by: shaolila <shaolila@buaa.edu.cn>
|
2026-09-16 02:17:07 -07:00 |
|
|
Harry MellorandClaude Opus 5
|
5f203baedb
|
[Docs] Split slash-combined docstring parameters (#57141)
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 02:16:32 -07:00 |
|
|
|
35f6047c1a
|
[XPU][Bugfix] Fix Qwen2-Audio ValueError on audio clips longer than 30s (#56912)
Signed-off-by: Jakub Byczkowski <jakub.byczkowski@intel.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-09-16 16:54:02 +08:00 |
|
|
Li, Jiang
|
b68408043d
|
[Bugfix][CPU] Add per-tensor FP8 W8A16 kernel to fix Ministral crash on CPU (#56985)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-09-16 15:49:17 +08:00 |
|
|
|
0f8fa53acf
|
[Bugfix][KV Offload] Check cgroup memory before SHM allocation (#54014)
Signed-off-by: Alex <jihui.huang@daocloud.io>
Signed-off-by: AlexHuang <alex.tech.lab@outlook.com>
Signed-off-by: Alex <alex.tech.lab@outlook.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Itay Etelis <92247226+Etelis@users.noreply.github.com>
|
2026-09-16 09:17:50 +03:00 |
|
|
Jiangyun ZhuandTJian
|
4fe9e6f6e5
|
[Refactor][GLM-5.3-Flash] Move sparse_attn_indexer_kpool into the model folder and split AMD/NVIDIA (#55358)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
|
2026-09-16 05:50:35 +00:00 |
|
|
danisereb
|
a31ec3a68b
|
[LoRA][Nemotron] Add LoRA support for Nemotron VL models (for the language model only) (#56231)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
|
2026-09-15 21:20:28 -07:00 |
|
|
Marceli FylcekandKunshang Ji
|
ccbaed5b91
|
[XPU] Route to fused_qk_rmsnorm_rope_gate triton kernel (#56096)
Signed-off-by: Marceli Fylcek <marceli.fylcek@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-09-16 11:05:54 +08:00 |
|
|
|
a4d2d9d95e
|
[ROCm][Kimi-K3] Enable a4w4 flydsl kernels for KimiK3 (#53940)
Signed-off-by: ppalanga <ppalanga@amd.com>
Signed-off-by: Poovaiah Palangappa <poovaiah.palangappa@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Poovaiah Palangappa <poovaiah.palangappa@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
|
2026-09-16 01:38:02 +00:00 |
|
|
Jared WenandClaude Fable 5.1
|
1257512305
|
[DSA] Wire DeepGEMM sparse MQA logits into the DeepSeek V4.1 indexer (#56254)
Signed-off-by: Jared Wen <w13431838023@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-15 14:07:14 -07:00 |
|
|
Nick Hill
|
f2aad6aa70
|
[MRV2] Buffer util simplifications (#56888)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-15 20:36:51 +00:00 |
|
|
Wentao Yeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
18f8aa0465
|
[Refactor] Remove dead kernel code (#56845)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-15 13:17:53 -07:00 |
|
|
|
9446ea1680
|
[Bugfix][Spec Decode] Only create draft_id_to_target_id when draft vocab differs (#53458)
Signed-off-by: drslark <slarksblood@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: GLM-5.3 <glm@z.ai>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-15 14:59:02 +00:00 |
|
|
Abhinav VermaandClaude Opus 5
|
1e47ec00d2
|
[Bugfix][Gemma 4] Don't read fft_length when profiling unified audio (#56721)
Signed-off-by: Abhinav Verma <verma.abhinav275@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-15 14:57:32 +00:00 |
|
|
|
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 |
|
|
|
567f745c1b
|
[Bugfix] Export weight-cache IPC tensors separately for each client (#56472)
Signed-off-by: 子华 <huaxi.shx@alibaba-inc.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-15 02:43:42 +00:00 |
|
|
JohnQinAMDandClaude Opus 5
|
ef5f7cd119
|
[ROCm][DSv4.1][Perf] Dequantize the MXFP8 weight once when dot_scaled cannot be used (#56560)
Signed-off-by: JohnQinAMD <yanyuan.qin@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-15 09:07:26 +08:00 |
|
|
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 |
|
|
Netanel Haber
|
d4ee7fe7a9
|
[Quantization] Select linear backends per quantization (#51204)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
|
2026-09-14 16:24:18 -04:00 |
|
|
Nicolò LucchesiandJorge Gallego Feliciano
|
995e8581f4
|
[Model] Voxtral Realtime: add support for CUDAGraphMode.FULL_DECODE_ONLY (#51167)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Jorge Gallego Feliciano <jorge.gallego@mistral.ai>
|
2026-09-14 19:16:39 +00:00 |
|
|
Yongye Zhu
|
5372e72a98
|
[Perf][DSv4.1] Fold the mHC post block into the delayed pre projection (#56633)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-09-14 18:57:37 +00:00 |
|
|
|
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 |
|
|
|
b3124a8237
|
[Model] Add support for Nanbeige4.2 (transformers backend) (#56071)
Signed-off-by: zqlcode <lizongqiang@kanzhun.com>
Signed-off-by: zql <37731799+zqlcode@users.noreply.github.com>
Co-authored-by: zqlcode <lizongqiang@kanzhun.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-14 15:06:01 +00:00 |
|
|
|
c676e4930b
|
[Spec Decode] Fix Qwen3 DSpark d2t requirement for padded-vocab drafts (#55133)
Signed-off-by: Orestis Zambounis <23146389+orestis-z@users.noreply.github.com>
Signed-off-by: Orestis Zambounis <orestis.zambounis@gmail.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-09-14 10:07:07 -04:00 |
|
|
linitra24
|
9d4d9aa5bc
|
[LoRA][Refactor] Unify multimodal LoRA token count hooks (#55071)
Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>
|
2026-09-14 13:19:15 +00:00 |
|
|
arkohutandHarry Mellor
|
6623fe5b4e
|
[Bugfix] MiniCPM-V 4.6: fix ViT self-attn qkv weight loading (#49417)
Signed-off-by: arkohut <39525455+arkohut@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-14 13:18:55 +00:00 |
|
|
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 |
|
|
Matthias Gehre
|
dc2e8f1157
|
[ROCm][Perf] W4A16: keep skinny GEMM zero-points packed 4-bit (#54965)
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
|
2026-09-14 17:40:25 +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 |
|
|
Isotr0py
|
dbf49dad11
|
[Fast Start] Use GPU uuid as socket folder identifier (#56669)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-14 06:28:13 +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 |
|
|
siyuandIsotr0py
|
52dd0d7562
|
[Fast Start] Fast loader support nnode>1 (#55468)
Signed-off-by: siyu <mg21330037@smail.nju.edu.cn>
Co-authored-by: Isotr0py <2037008807@qq.com>
|
2026-09-14 03:05:54 +00:00 |
|
|
Woosuk Kwon
|
3b533197a9
|
[Perf] Parallelize mHC pre-norm JIT warmup (#56683)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-09-13 18:58:20 -07:00 |
|
|
Woosuk KwonandOpenAI Codex
|
71888f507a
|
[Perf] Avoid redundant conversions in FP8 dummy initialization (#56688)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-13 12:06:13 -07:00 |
|
|
Kevin H. Luu
|
dec0b5d63f
|
[Bugfix] Skip Triton autotune inspection without Triton (#56676)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-09-13 17:05:29 +00:00 |
|
|
|
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 |
|
|
Woosuk Kwon
|
e7a3963339
|
[Bugfix] Avoid repeated dummy initialization and random CPU Engram fills (#56682)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-09-13 02:23:20 -07:00 |
|
|
YleanandCodex
|
a987777755
|
[Bugfix][Gemma4] Keep image kwargs out of video preprocessing (#56652)
Signed-off-by: Ylean <61880605+Woolgathererer@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-13 09:07:12 +00:00 |
|