 aoshen02
|
4eef91c03c
|
[Model] Support R3 capture with DeepGEMM MegaMoE (#51831)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
|
2026-08-12 01:07:07 -07:00 |
|
|
Matej SirovatkaandJee Jee Li
|
3ac9525507
|
[Bugfix][Quantization] Reuse online NVFP4 MoE kernel across reloads (#50074)
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-12 14:06:53 +08:00 |
|
|
aoshen02andCodex
|
f2906b492e
|
[Bugfix] Avoid repeated layerwise reload warning scans (#49505)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>
|
2026-08-12 13:53:50 +08:00 |
|
|
Matvei PashkovskiiandClaude
|
20727e2841
|
[Hardware][AMD] Enable fused bf16→fp32 router GEMM on ROCm (#50268)
Signed-off-by: Matvei Pashkovskii <mpashkov@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-12 02:46:13 +00:00 |
|
|
Nick Hill
|
f97e502969
|
[Perf] Avoid more GPU<->CPU syncs on the model execution path (#51738)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-11 19:30:34 -07:00 |
|
|
Simon Danielsson
|
47ececb58e
|
[Perf][ROCm] Dual-stream decode with hipgraphs (#48223)
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
|
2026-08-12 09:32:24 +08:00 |
|
|
PikaPikachu
|
466855a2bf
|
[ROCm] Enable DeepSeek-V4 on gfx11 (#47017)
This PR enables DeepSeek-V4 checkpoints on ROCm gfx11/RDNA devices.
Signed-off-by: Letian Kang <Letian.Kang@amd.com>
|
2026-08-12 08:55:10 +08:00 |
|
|
Rohan PotdarandClaude Opus 4.8
|
0f0cb918b7
|
[ROCm][MoE] Fix expert_map vs AITER expert_mask for non-AITER experts under EP (#49758)
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-08-11 15:33:02 -05:00 |
|
|
Andreas Karatzasandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
36f4630d89
|
[Bugfix][MoE] Fix fused block-scale orientation (#50727)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-11 16:05:38 -04:00 |
|
|
Wentao Ye
|
fd04edef3e
|
[Refactor] Delete dead code in models (#51838)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-11 15:44:26 -04:00 |
|
|
Andreas KaratzasandOpenAI Codex
|
1ab2801dde
|
[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-11 14:19:16 -04:00 |
|
|
Julien Debache
|
52be12cfac
|
feat: allow shared expert overlapping for FlashInfer one-sided all-to-all (#50569)
Signed-off-by: jdebache <jdebache@nvidia.com>
|
2026-08-11 10:06:22 -07:00 |
|
|
Harry Mellor
|
c65aa2ee6c
|
Bump Transformers version to 5.15.0 (#51668)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-11 09:00:51 -07:00 |
|
|
Jiangyun ZhuandOpenAI Codex
|
5af7c8dad7
|
[Bugfix] Align Qwen GDN gates with speculative tokens (#51812)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-11 23:35:30 +08:00 |
|
|
pmanczakandKunshang Ji
|
5b5eae2394
|
[Misc] Enable test_silu_mul_fp8_quant_deep_gemm on XPU (#49444)
Signed-off-by: pmanczak <pawel.manczak@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-11 23:19:14 +08:00 |
|
|
|
0fb9897df1
|
[Bugfix][MoE] Support GELU tanh in FlashInfer B12x MoE (#51819)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-11 15:07:58 +00:00 |
|
|
Jee Jee Li
|
dd7cc85f17
|
Add MoE output contract for MoE tail fusion (#51407)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-08-11 22:23:59 +08:00 |
|
|
|
6c95a641e9
|
[2/N][Feat][Perf] Add new warmup infrastructure for JITs. Add predicate filtering for JIT warmup, and migrate Inkling FA4 (#49315)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@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>
|
2026-08-11 07:46:07 -04:00 |
|
|
liushujia122
|
d8f840071e
|
[Model] Enable tower and connector LoRA for Keye (#51780)
Signed-off-by: shujialiu <liushujia0122@163.com>
|
2026-08-11 10:35:59 +00:00 |
|
|
zofiaandKunshang Ji
|
52c70b210c
|
[XPU] [Linear] enable torch linear backend for blockwise gemm on xpu (#50826)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-11 16:43:33 +08:00 |
|
|
Fangzhou Ai
|
1044d19998
|
[ROCm][DSV4] Preserve native MXFP4 TP8 shard allocation (#51473)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
|
2026-08-10 23:57:27 -07:00 |
|
|
Harry Mellor
|
be2e274ef5
|
Fix docs on main (#51773)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-10 23:52:04 -07:00 |
|
|
Priyansh JainandAndreas Karatzas
|
2acb055ed7
|
[CPU][Zen] Route BF16 MoE inference through zentorch on AMD (#44201)
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-10 23:20:05 -07:00 |
|
|
Wei Zhao
|
608c12473f
|
[Attention] Fix MLA prefill workspace allocation size (#51733)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-11 05:34:30 +00:00 |
|
|
|
c76a425278
|
[Kernel] Optimize long-context MLA cache gathers (#51739)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-10 22:23:43 -07:00 |
|
|
Khushali Desaiandwang.yuqi
|
dc5101fb1b
|
replace batch_norm to numerically identical without cudnn (#51734)
Signed-off-by: khushali9 <khushali.desai9@gmail.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-08-11 12:43:20 +08:00 |
|
|
Clinton ThomasandLucas Bourtoule
|
90fd4a333f
|
Preserve revision pins in secondary artifact loaders (#51446)
Signed-off-by: Clinton Thomas <1033162+KernelClint@users.noreply.github.com>
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
|
2026-08-11 04:33:10 +00:00 |
|
|
aoshen02andRoger Wang
|
99e62b802c
|
[Bugfix][Model Loader] Defer post-load attention weight processing (#49519)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-08-10 19:16:57 -07:00 |
|
|
Qiuyang Yue
|
b2506d62ae
|
[MM][CG][BugFix] Fix Ernie-4.5-VL encoder CG postprocess for multi-path outputs (#51461)
Signed-off-by: qyYue1389 <yueqiuyang1389@gmail.com>
|
2026-08-11 00:39:04 +00:00 |
|
|
Almog Tavor
|
c3cac8c63d
|
[Bugfix][MiMo] Apply vision attention sinks in the window attention path (#49815)
Signed-off-by: almogtavor <almogtavor@gmail.com>
|
2026-08-10 22:36:42 +00:00 |
|
|
|
63ac04a61e
|
[Kimi-K3] DCP support (#50484)
Signed-off-by: girasoley <girasoley@inferact.ai>
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
Signed-off-by: 云挚 <ningyunxiao.nyx@antgroup.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: 云挚 <ningyunxiao.nyx@antgroup.com>
Co-authored-by: foraxe <73625538+foraxe@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-08-10 12:54:26 -07:00 |
|
|
|
8fea1d306f
|
Fix uniform_random routing simulation to sample without replacement (#43680)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-08-10 15:28:57 +00:00 |
|
|
Harry Mellor
|
cf8f3a3bb2
|
[2/N] Harden Transformers modelling backend multi-modal path (#51657)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-10 12:57:12 +00:00 |
|
|
Harry Mellor
|
70b84f0bcb
|
Fix Gemma 4 for upcoming Transformers version (#49797)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-10 07:48:26 +00:00 |
|
|
|
ba1cdcfcf0
|
[Model][Quantization] Add Ling-3.0-flash-fp8 support (#51265)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-09 23:09:08 -07:00 |
|
|
Isotr0py
|
3b4c86e489
|
[Bugfix][Quantization] Fix fp32 weight scale for mxfp4 quantization and per-expert checkpoint mapping (#51419)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-08-09 23:08:52 -07:00 |
|
|
Li, Jiang
|
7ce84b99ce
|
[CPU] Restore linear dispatch for small unquantized GEMMs (#51379)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-08-10 11:29:59 +08:00 |
|
|
Lena OnyshchenkoandKunshang Ji
|
751f2ccdd3
|
[Kernel][XPU] Tensor-descriptor operand loads for Triton W8A8 scaled_mm (#47205)
Signed-off-by: oonyshch <xonyshch@gmail.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-08-10 00:56:11 +00:00 |
|
|
|
f18e10a7e1
|
Bump Flashinfer version to 0.6.16.post3 (#50892)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
|
2026-08-09 00:54:07 -07:00 |
|
|
Isotr0py
|
073c510c91
|
[Migration] Migrate bitsandbytes support to OOT plugin (#43529)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-08-09 10:27:31 +08:00 |
|
|
Nick Hill
|
9b0afeb4f6
|
[Perf] Avoid some more unnecessary GPU<->CPU syncs (#51458)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-08 17:13:26 -07:00 |
|
|
ylsunandClaude Opus 5
|
0fe9a916e8
|
[Bugfix] Fix LFM2 ShortConv prefix breaking quant ignore list (#51495)
Signed-off-by: ylsun <1654366371@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-08 11:27:13 +00:00 |
|
|
Tianyu Guo
|
653ebb52df
|
Add torch compile for qwen3_vl encoder (#40116)
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
|
2026-08-08 08:23:18 +00:00 |
|
|
Andreas Karatzas
|
6e18901195
|
[Bugfix][MM] Avoid device sync in FusedInputNorm initialization (#51435)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-08-08 13:32:23 +08:00 |
|
|
djramic
|
5eaa70dac5
|
[Bugfix][Quantization] Fix INT8 W8A8 MoE crash in TritonExperts (#51411)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-08-07 22:06:58 -05:00 |
|
|
Linkun
|
7f58e8294a
|
[Kimi][MM] disable kimi_vit's dynamic torch.compile for TPU (#51196)
Signed-off-by: Linkun Chen <github@lkchen.net>
|
2026-08-08 00:42:51 +00:00 |
|
|
Andrii SkliarandAleksandr Skliar
|
a801e71cb8
|
[Perf] Improve --linear-backend filtering (#48735)
Signed-off-by: Aleksandr Skliar <askliar@nvidia.com>
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Aleksandr Skliar <askliar@nvidia.com>
|
2026-08-07 15:15:54 -07:00 |
|
|
Nick Hill
|
9823714346
|
[Bugfix] Drop stale layer kwarg from online MXFP4 kernel creation (fix precommit) (#51442)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-07 13:49:00 -07:00 |
|
|
Wei-Ming Chen
|
1c94e8dc7d
|
Add NVFP4 KV 4-over-6 scale search (#45187)
Signed-off-by: weimingc <17592131+meenchen@users.noreply.github.com>
|
2026-08-07 13:22:27 -07:00 |
|
|
Walter Beller-MoralesandHarry Mellor
|
70456e5e6f
|
[Bugfix] when loading weights skip empty expert bias if model does not support them (#50937)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-08-07 12:45:52 -07:00 |
|