|
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 |
|
|
Wentao Ye
|
3709632ff2
|
[Refactor] Remove dead code multiple places (#60120)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-10-10 15:41:10 +00:00 |
|
|
Mook
|
bf16c9c139
|
[Bugfix][Model] K-EXAONE: restore loading of pre-2.0 configs and apply RoPE to the MTP layer (#60187)
Signed-off-by: godmook <cmoh4135@naver.com>
Signed-off-by: Mook <68294499+Godmook@users.noreply.github.com>
|
2026-10-10 15:05:55 +00:00 |
|
|
SeongJun Leeandlesj0610
|
a98247ab4d
|
[Model] Drop the 4x M-RoPE cache headroom for Qwen3-VL, Qwen3.5 and Qwen3.8 (#59853)
Signed-off-by: lesj0610 <lesj0610@users.noreply.github.com>
Signed-off-by: lesj0610 <lesj0610@gmail.com>
Co-authored-by: lesj0610 <lesj0610@users.noreply.github.com>
|
2026-10-10 06:51:52 +00:00 |
|
|
SeongJun LeeandIsotr0py
|
699c892dd5
|
[Perf] Skip the M-RoPE warmup when every holder of the RoPE fuses it (#60246)
Signed-off-by: lesj0610 <lesj0610@gmail.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-10-10 06:47:39 +00:00 |
|
|
liuzhenweiandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ff440c7805
|
[BreakableCG] Add eager break for Mamba-family ops (#57881)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-10 14:06:57 +08:00 |
|
|
Andreas KaratzasandClaude
|
a205fb3177
|
[Bugfix][Model] Restore AXK1 config defaults dropped with the vendored config (#60954)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-10 05:54:52 +00:00 |
|
|
devpramodandClaude Opus 5.5
|
46fb84c2d4
|
[Model] Support EAGLE3/DFlash aux hidden states for Granite (#60855)
Signed-off-by: Pai, Pramod <pramod.pai@intel.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-10-10 13:34:10 +08:00 |
|
|
linitra24
|
364bc81a9e
|
[Bugfix][LoRA] Fix GPT-OSS gate/up interleaving with mixed MoE LoRA formats (#60812)
Signed-off-by: linitra24 <renshuang.zhou@daocloud.io>
|
2026-10-10 12:52:51 +08:00 |
|
|
Guancheng FuandKunshang Ji
|
acec1b1d84
|
[Bugfix][XPU] Remove stale W4A8 weight after repacking (#57511)
Signed-off-by: Guancheng Fu <guancheng.fu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-10-10 04:27:35 +00:00 |
|
|
|
2d69083c4a
|
[ROCm][MXFP4] Align the AITER W4A4 MoE intermediate size to 128 (#55104)
Signed-off-by: xiaofei.zheng <xiaofei.zheng@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
|
2026-10-10 11:14:01 +08:00 |
|
|
|
02aa10539f
|
[Bugfix][ModelLoader] Make enable_weights_track check quantized layers (#57108)
Signed-off-by: siliangchen-amd <SiLiang.Chen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-10-10 10:44:06 +08:00 |
|
|
|
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 |
|
|
Ning XieandSimon Mo
|
a0f28d73a8
|
[sharded state loader] support pp in sharded state loader (#52110)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
|
2026-10-09 11:08:31 -07:00 |
|
|
Juan Pérez de Algabaandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
3d52578e13
|
[Security] Do not retain Phi-4 MM audio attention matrices (#60614)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-09 22:23:35 +08:00 |
|
|
Yan Ma
|
c17fadcfdc
|
[XPU] fix fused_input_norm for MM (#59865)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-10-09 20:16:35 +08:00 |
|
|
YiSheng5andKunshang Ji
|
0cc0460870
|
[XPU]Fix the accuracy issue when meet topk_ids=-1 on DP+EP scenarios (#57787)
Signed-off-by: yisheng <yi.sheng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-10-09 20:01:54 +08:00 |
|
|
Damien LaineandCyrus Leung
|
2186b89a9a
|
[Bugfix][Model] Voxtral realtime: fix boot OOM and engine crash at max_model_len (#45022)
Signed-off-by: Damien Laine <damien.laine@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-10-09 17:40:29 +08:00 |
|
|
Harry MellorandClaude Opus 5.5
|
2c99ee9333
|
[Chore] Remove vendored code made redundant by Transformers 5.16.1 (#60623)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-09 09:29:03 +00:00 |
|
|
|
19c0bed584
|
[Fusion] Support 3D activation quantization fusion and enable it for Pixtral (#59612)
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-10-09 15:12:03 +08:00 |
|
|
Paweł MańczakandKunshang Ji
|
f0a5f111f2
|
[XPU] Add tuned Mamba SSU configs for Intel Arc Pro B60 (#56765)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-10-09 14:29:29 +08:00 |
|
|
Nishant RevurandClaude
|
581692cc0f
|
[Bugfix][Spec Decode] Fix multimodal embedding merge in Llama 4 and Mistral Large 3 EAGLE drafters (#57633)
Signed-off-by: Nishant Revur <kumrfni@amazon.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-09 01:44:50 +00:00 |
|
|
Misha GoinandClaude
|
e3a29aa9b3
|
[Bugfix][MoE] Size the permute scratch from its inputs (#60447)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-08 15:32:07 -04:00 |
|
|
Misha GoinandClaude
|
30c7405890
|
[MoE] MXFP4 oracle: add CUTLASS W4A4 backend and BF16 activation fallback (#60079)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-10-08 11:39:09 -07:00 |
|
|
|
d8fa463e2b
|
[Bugfix][Prefix caching] Fix inconsistent hybrid Mamba prefix cache boundaries (#60533)
Signed-off-by: Wei Zhao <weizha@aws-cmh-slurm-1-login-01.cm.cluster>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Wei Zhao <weizha@aws-cmh-slurm-1-login-01.cm.cluster>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-08 18:33:48 +00:00 |
|
|
|
9f3d70e081
|
[Quantization] Enable shared expert fusion compatibility with online shared_expert quantization (showcase: along Quark MXFP4 routed experts) (#55686)
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-10-08 12:04:46 -04:00 |
|
|
JartX
|
994b8b77be
|
[Bugfix][ROCm] RDNA3 W4A16 MoE: handle the N-first CT weight layout (#60388)
Signed-off-by: JartX <sagformas@epdcenter.es>
|
2026-10-08 15:06:39 +00:00 |
|
|
Matthew BonanniandClaude Opus 5.5
|
4ed4c4433b
|
[Bugfix][HiSparse] Drop the unaccounted, write-only prefill mirror staging buffer (#60429)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 14:00:49 +00:00 |
|
|
Harry MellorandClaude Opus 5.5
|
21d9758459
|
Remove Python 3.10 support now that it is EOL (#60402)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-08 02:30:52 -07:00 |
|
|
liuzhenweiandKunshang Ji
|
0004536dd0
|
[XPU][Graph] Replace boolean-mask assignment with torch.where (#60529)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-10-08 17:13:48 +08:00 |
|
|
Paweł Mańczak
|
4cf1307e72
|
[XPU] Add tuned Mamba SSU configs for 2 more B70 shapes (#57565)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
|
2026-10-08 16:36:05 +08:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
814301b268
|
[Bugfix][Quant] Read safetensors headers of checkpoints with other file names (#60411)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-10-08 01:38:41 -05:00 |
|
|
Jiahan Chang (Cyrus)
|
816173ca9d
|
[Kernel] Remove WAR for LL CuTeDSL BF16 GEMM (#60434)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
|
2026-10-08 05:38:07 +00:00 |
|
|
|
81198e97ba
|
[Refactor] Abstract DeepGemm MegaMOE backend (#58053)
Signed-off-by: Hui Shi <kalinshi@tencent.com>
Co-authored-by: LuneExplorer <liyihan23@mails.tsinghua.edu.cn>
Co-authored-by: ArmageddonKnight <bojian@cs.toronto.edu>
|
2026-10-08 05:05:39 +00:00 |
|
|
|
775792f2d5
|
[Bugfix] Reland #53020: tie lm_head.weight for Nemotron Parse when checkpoint omits it (#60272)
Signed-off-by: Anish Kumar <aniskumar@nvidia.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-10-08 04:40:55 +00:00 |
|
|
Isotr0pyandShanshan Shen
|
8352b2427f
|
[Multimodal] Optimize encoder cudagraph padding logic (#58925)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-10-08 03:38:09 +00:00 |
|
|
MattandClaude Opus 5.5
|
9dba339d07
|
[Bugfix][ROCm] Keep MLA derived weights in place on weight reload (#60389)
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-10-07 20:38:06 -05:00 |
|
|
|
f38c6778ce
|
[quantization] Add per-token NVFP4 quantization MoE support for ReLU2 (#56740)
Signed-off-by: Xuanteng Huang <xuantengh@nvidia.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-10-07 22:01:09 +00:00 |
|
|
|
b803edbc9f
|
[Model] Streamline EmbeddingGemma 2 config resolution and harmonize Triton prefill attention (#60289)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-10-07 14:56:40 -07:00 |
|
|
Misha GoinandClaude Opus 5.5
|
a982c81e3e
|
[Bugfix] Limit GlmMoeDsaForCausalLM fp8 KV cache default to SM100 (#60281)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-07 13:37:13 -07:00 |
|
|
|
e572e02d21
|
[UX] Skip checkpoint shards an MTP head does not load (#60152)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-07 15:16:19 -04:00 |
|
|
Jinzhen LinandKevin H. Luu
|
32fbfa15e8
|
[Bugfix][Quantization] Accept folded NVFP4 scales for Humming A16 (#60337)
Signed-off-by: jinzhen.ljz <jinzhen.ljz@antgroup.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
|
2026-10-07 11:04:43 -07:00 |
|
|
|
fba462e008
|
[Bugfix]Fix FlashInfer warmup crash: autotune(tuning_buckets=...) must round M up, not down (Invalid MXFP8 split-K tactic with spec-decode) (#58165)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-07 14:01:21 -04:00 |
|
|
pmanczak
|
f7f62d1916
|
[XPU][MoE] Tune Triton fused MoE for Intel XPU (#53065)
|
2026-10-08 00:02:13 +08:00 |
|
|
xaguilar-amdandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9367d8b969
|
[Bugfix][MLA] Scope DSpark non-causal capability to builder layers (#57992)
Signed-off-by: Xavier Aguilar <xavier.aguilarfruto@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-07 10:22:32 -05:00 |
|
|
Mikko TukiainenandCursor
|
548597367e
|
[ROCm][Perf] Add AITER FlyDSL GDN prefill backend (#57560)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-10-07 09:44:22 -05:00 |
|
|
|
c83935b300
|
[Bugfix][Model Loader] Support reload_weights with runai_streamer load format (#58124)
Signed-off-by: Viktor Koukouliev <vkoukouliev@nvidia.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-10-07 14:04:35 +00:00 |
|
|
00CC
|
5281e49908
|
[ROCm][Perf] Enable medium-skinny dispatch in RDNAHybridW4A16LinearKernel (#52619)
Signed-off-by: tangzzycc <3081129260@qq.com>
|
2026-10-07 13:21:43 +00:00 |
|
|
SeongJun Lee
|
6b75dfb8a1
|
[Misc] Report a missing DeepSelect extension only when it is requested (#60242)
Signed-off-by: lesj0610 <lesj0610@gmail.com>
|
2026-10-07 09:53:17 +00:00 |
|
|
Robert ShawandClaude Code
|
283d76d56a
|
[Bugfix] Widen ep_gather output offset to int64 (#58373)
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
|
2026-10-07 01:45:04 +00:00 |
|