 Kyuyeun Kim
|
0a0a1a198b
|
Add ability to replace oot ops when using lora (#37181)
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
|
2026-03-16 18:04:15 -07:00 |
|
|
Julien Denize
|
7961486a9b
|
Fix EagleMistralLarge3Model initialization (#37232)
Signed-off-by: juliendenize <julien.denize@mistral.ai>
|
2026-03-16 15:41:00 -07:00 |
|
|
EdalatiAli
|
e5b807607c
|
[Quant][Feature] Support online MXFP8 quantization for MoE and dense models (#35448)
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
|
2026-03-16 18:07:39 -04:00 |
|
|
|
fd4d96302a
|
Fix eplb nvfp4 experts hook (#37217)
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Signed-off-by: Elvir Crncevic <elvir@anthropic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-03-16 22:03:54 +00:00 |
|
|
Lucas Kabela
|
714c6e0eab
|
[torch.compile][BE] Modify cudagraph callable to check for is_forward_context_set (#36288)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
|
2026-03-16 19:42:34 +00:00 |
|
|
haosdentandOr Ozeri
|
ca1954d58c
|
[Bugfix] Disable cross-layer KV cache for MLA attention backends (#37090)
Signed-off-by: haosdent <haosdent@gmail.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
|
2026-03-16 19:03:10 +02:00 |
|
|
Tianyu Guo
|
43a73f853b
|
Remove unused EVS functions in qwen3_vl.py (#37183)
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
|
2026-03-16 13:09:09 +00:00 |
|
|
Lukas GeigerandIsotr0py
|
f9e6db3034
|
[Models][Qwen3 ViT] Keep max_seqlen on CPU to prevent D2H sync (#37139)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-03-16 12:11:59 +00:00 |
|
|
Artem Perevedentsev
|
f5e59ee7a6
|
[Performance] Add prefetch for checkpoints to OS page cache (#36012)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-03-16 11:32:02 +00:00 |
|
|
Harry Mellor
|
ad041c79db
|
Fix text only inputs for MRoPE models with the Transformers modelling backend (#37055)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-03-16 10:31:16 +00:00 |
|
|
Kunshang Ji
|
747b068136
|
[Hardware] Replace memory related torch.cuda APIs (#37031)
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
|
2026-03-16 10:24:48 +00:00 |
|
|
Harry Mellor
|
122f75d939
|
Fix pipeline parallel with multimodal models with the Transformers modelling backend (#37057)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-03-16 10:20:37 +00:00 |
|
|
Vadim Gimpelson
|
8374387bd8
|
[FlashInfer] Revert block_size 16 + head_size 256 workaround on Blackwell (#36987)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2026-03-16 09:04:29 +00:00 |
|
|
Isotr0py
|
912fbe9555
|
[Bugfix] Fix Qwen2.5-Omni/Qwen3-Omni use_audio_in_video with multi-video inputs (#37147)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-03-16 08:56:06 +00:00 |
|
|
Roy Wang
|
821eb80c0d
|
[Performance][Model Loader] Skip non-local expert weights during EP model loading (#37136)
Signed-off-by: esmeetu <jasonailu87@gmail.com>
|
2026-03-16 01:33:36 -07:00 |
|
|
|
2754231ba3
|
[Kernel] Add FlashInfer MoE A2A Kernel (#36022)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Leo Tian <lctian@nvidia.com>
Co-authored-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: root <root@lyris0267.lyris.clusters.nvidia.com>
|
2026-03-15 23:45:32 -07:00 |
|
|
bigshanedogg
|
2390d44209
|
[Model] Add HyperCLOVAX-SEED-Think-14B language model support (#37107)
Signed-off-by: bigshanedogg <bigshane319@gmail.com>
|
2026-03-16 06:40:05 +00:00 |
|
|
Wang, Yiting
|
68e1b711f1
|
[XPU] Add deepseek_scaling_rope fused kernel (#36612)
Signed-off-by: yitingw1 <yiting.wang@intel.com>
|
2026-03-16 12:35:08 +08:00 |
|
|
|
7acaea634c
|
In-Tree AMD Zen CPU Backend via zentorch [1/N] (#35970)
Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Chinmay-Kulkarni-AMD <Chinmay.Kulkarni@amd.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-03-15 23:35:35 +00:00 |
|
|
Jiangyun ZhuandRoger Wang
|
697e4ff352
|
[GDN] add a config for gdn kernel selection (#36647)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-03-16 00:40:17 +08:00 |
|
|
Hari
|
a3e2e250f0
|
[Feature] Add Azure Blob Storage support for RunAI Model Streamer (#34614)
Signed-off-by: hasethuraman <hsethuraman@microsoft.com>
|
2026-03-15 19:38:21 +08:00 |
|
|
arlo
|
8c29042bb9
|
[Feature] Add InstantTensor weight loader (#36139)
|
2026-03-14 18:05:23 +01:00 |
|
|
Isotr0py
|
a8e8d62dd8
|
[Misc] Clean up Kimi-audio whisper encoder loading (#36903)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-03-14 23:37:52 +08:00 |
|
|
Harry Mellor
|
ffa5d74f15
|
Enable loading of fused expert weights in the Transformers modelling backend (#36997)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-03-14 07:01:06 +00:00 |
|
|
Dimitrios BariamisandDimitrios Bariamis
|
367cf5cd3e
|
[Feat][Bugfix] Enable additional dimension for Flashinfer MLA and fix routing dtype (#36931)
Signed-off-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
Co-authored-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com>
|
2026-03-13 16:41:16 -07:00 |
|
|
haosdent
|
6d53efd2a5
|
[Bugfix] Fix MLA attention crash with AWQ/GPTQ quantized models (#34695)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-03-13 23:25:41 +00:00 |
|
|
Benjamin Chislett
|
8b346309a5
|
[Refactor] Consolidate SupportsEagle (#36063)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-03-13 23:22:40 +00:00 |
|
|
Harry Mellor
|
0005d2a3c9
|
Use Transformers v5 WeightRenaming for Transformers modeling backend (#31545)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-03-13 20:49:08 +00:00 |
|
|
Divakar Verma
|
6341d43043
|
[ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
|
2026-03-13 19:44:24 +00:00 |
|
|
Isotr0py
|
abf61aaa8e
|
[Bugfix] Fix Qwen2.5-omni/Qwen3-omni mm_processor cache for audio_in_video request (#36800)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-03-13 18:16:05 +00:00 |
|
|
|
4508532fbd
|
[Bugfix] fix paddleocr crash on some image shape (#36959)
Signed-off-by: wangzhengtao <wangzhengtao@msh.team>
Signed-off-by: bigmoyan <moyan_work@foxmail.com>
Co-authored-by: wangzhengtao <wangzhengtao@msh.team>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-03-13 13:46:55 +00:00 |
|
|
|
d5af196c18
|
[2/N] Elastic EP Milestone 2: Integrating NIXL-EP (#35627)
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
|
2026-03-13 09:25:33 -04:00 |
|
|
Thomas Parnell
|
f296a1966d
|
[Bugfix] Fix FlashInfer GDN warmup ValueError on SM90 GPUs (#36876)
|
2026-03-13 07:09:39 +01:00 |
|
|
whyiugandwang.yuqi
|
1ce13cf992
|
[Model] Add support for BERT-like Chinese ERNIE pooling models (#36385)
Signed-off-by: whyiug <whyiug@hotmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-03-13 03:23:53 +00:00 |
|
|
NikitaandCyrus Leung
|
10f08dedfa
|
[Model] Add ColPali late interaction model for multi-modal retrieval (#36818)
Signed-off-by: Nikita Sukharev <kaonael@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-03-13 02:18:57 +00:00 |
|
|
Yifan Qiao
|
55d8073d06
|
[Bugfix] ep_scatter kernel store-load race condition (#34991)
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
|
2026-03-13 01:07:59 +00:00 |
|
|
Jaewon
|
aaa3092f51
|
[MoE] Add routing simulation override for MXFP4 quantized MoE (#33595)
Signed-off-by: Jaewon Lee <jaewon@meta.com>
|
2026-03-13 00:30:44 +00:00 |
|
|
|
87985077a4
|
[Speculative Decoding] Add norm_before_fc for gpt-oss draft models (#36545)
Signed-off-by: Shubhra Pandit <shubhra.pandit@gmail.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-03-12 23:03:32 +00:00 |
|
|
Xinan MiaoandSouthWest7
|
2cdf92228c
|
[Feature]: Remove Chunking From FusedMoE (#34086)
Signed-off-by: SouthWest7 <am1ao@qq.com>
Signed-off-by: Southwest <1403572259@qq.com>
Signed-off-by: southwest <am1ao@qq.com>
Signed-off-by: Xinan Miao <1403572259@qq.com>
Co-authored-by: SouthWest7 <am1ao@qq.com>
|
2026-03-12 14:24:38 -04:00 |
|
|
Matthew Bonanni
|
f444c05c32
|
[Attention] Use FA4 for MLA prefill (#34732)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-03-12 12:10:17 -04:00 |
|
|
Kunshang Ji
|
53ec16a705
|
[Hardware] Replace torch.cuda.device_count/current_device/set_device API (#36145)
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-03-12 07:57:47 -07:00 |
|
|
Wei ZhaoandMichael Goin
|
2e693f48e7
|
[Perf] Add TRTLLM FP8 MoE Modular Kernel (#36307)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-03-12 07:32:31 -07:00 |
|
|
caozuobaandRoger Wang
|
9e19f8338b
|
[Perf] add packed recurrent fast path for decode (#36596)
Signed-off-by: hdj <1293066020@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-03-12 04:01:57 -07:00 |
|
|
Shanshan ShenandIsotr0py
|
f0d3658c0f
|
[MM][OOT] Support CPU seq_lens for OOT MMEncoderAttention kernels (#36605)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-03-12 03:28:23 -07:00 |
|
|
Michael GoinandClaude
|
57431d8231
|
[UX] Only show FP4 Marlin fallback warning for w4a4 models (#36806)
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-03-12 05:19:35 -04:00 |
|
|
Xu Jinyang
|
3e64fe4a18
|
[Bugfix] Warm up Triton autotuner for GDN layers during V1 profiling (#36599)
Signed-off-by: AuYang <459461160@qq.com>
|
2026-03-12 00:51:09 -07:00 |
|
|
István Ketykó
|
00726c74c9
|
[Bugfix][Model] Fix DeepSeek-OCR TensorSchema crash on empty images_crop (#36670)
Signed-off-by: István Ketykó <istvan.ketyko@gmail.com>
|
2026-03-12 15:35:54 +08:00 |
|
|
Yan Ma
|
894843eb25
|
replace with torch.cuda.device with with torch.accelerator.device_index (#36144)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-03-11 23:12:57 -07:00 |
|
|
Amanzhol Salykov
|
8a24842765
|
[ROCm] add tuned moe_wna16_triton kernel configs for CDNA4 (#35093)
Signed-off-by: salykova <amsalykov@gmail.com>
Signed-off-by: amd-asalykov <asalykov@amd.com>
|
2026-03-11 19:00:08 +00:00 |
|
|
Harry Mellor
|
65986db6ba
|
Make Gemma and Gemma 2 accept inputs_embeds like Gemma 3 (#36787)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-03-11 18:12:43 +00:00 |
|