|
f5972a872f
|
[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726)
Signed-off-by: Shahar Mor <smor@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2026-02-24 09:49:56 -08:00 |
|
|
Harry Mellor
|
c38b8d5a31
|
Remove padding_index from models that don't use it for better Transformers v5 compatibility (#35189)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-02-24 08:04:46 -08:00 |
|
|
Dor HuriandJee Jee Li
|
012dee9233
|
[Feature] Add LoRA tower/connector support for Llama 4 Vision (mllama4) (#35147)
Signed-off-by: dorhuri123 <dor.huri1@live.biu.ac.il>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-02-24 04:10:32 -08:00 |
|
|
Tugsbayasgalan ManlaibaatarandNicolò Lucchesi
|
f1c664545b
|
Make voxtral compile friendly (#33959)
Signed-off-by: Tugsbayasgalan Manlaibaatar <tmanlaibaatar@fb.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
|
2026-02-24 09:33:35 +01:00 |
|
|
Vadim Gimpelson
|
33a0d43c71
|
[BUGFIX][Qwen3.5] Hardcode mlp.gate as not quantizable (#35156)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2026-02-23 19:42:24 -08:00 |
|
|
Cyrus Leung
|
392645454b
|
[Refactor] Decouple TimingContext from InputProcessingContext (#35083)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-02-23 14:15:50 +00:00 |
|
|
Eldar KurtićandEldar Kurtic
|
1e8438a89a
|
[Llama4,CI] Bring back Llama-4 bug fixes, and also fix Maverick tests (#35033)
Signed-off-by: Eldar Kurtic <you@example.com>
Co-authored-by: Eldar Kurtic <you@example.com>
|
2026-02-23 09:04:34 -05:00 |
|
|
Robert ShawandRobert Shaw
|
8435b2e049
|
[ModelBash][DSV3] Add TRTLLM DSV3 Router GEMM kernel (6% B1 Speedup) (#34302)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-02-23 14:02:26 +00:00 |
|
|
Wentao Ye
|
7f40e9e516
|
[Refactor] Remove dead private func _fp8_perm and _extract_mask_for_item (#35068)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-02-23 05:05:20 -08:00 |
|
|
Harry Mellor
|
103e614b14
|
Fix pipeline parallel with embed scaling in the Transformers modelling backend (#35094)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-02-23 05:04:47 -08:00 |
|
|
|
e631f8e78e
|
fix: Apply embedding_multiplier to inputs_embeds (#34813)
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-02-23 00:42:46 -08:00 |
|
|
Cyrus Leung
|
987506bca6
|
[Refactor] Simplify dummy data generation (#35025)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-02-22 20:55:27 -08:00 |
|
|
qizixiandLu Fang
|
2bcf71b9c0
|
[Spec Decode] Reduce TP communication for speculative decoding draft token generation (#34049)
Signed-off-by: qizixi <qizixi@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
|
2026-02-22 14:59:16 -08:00 |
|
|
|
b7892a3bef
|
[Model] Add NVFP4 quantization support for Step3.5-Flash (#34478)
Signed-off-by: tacos8me <ian@cloudhabit.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-22 12:30:46 -07:00 |
|
|
Athrael Soju
|
970861ac0c
|
[New Model] Add ColModernVBERT (#34558)
Signed-off-by: Athrael Soju <athrael.soju@gmail.com>
Signed-off-by: athrael-soju <athrael-soju@users.noreply.github.com>
|
2026-02-22 12:23:41 +08:00 |
|
|
|
98b0205c3c
|
[Frontend] Add automatic language detection for Whisper transcription (#34342)
Signed-off-by: space_check <roman.vuskov@rwth-aachen.de>
Signed-off-by: Roman <45857014+spacecheck@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
|
2026-02-21 04:49:41 -08:00 |
|
|
Kata Coder
|
5719a4e4e6
|
[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574)
Signed-off-by: craftsangjae <craftsangjae@gmail.com>
|
2026-02-20 20:01:40 -08:00 |
|
|
|
11be2c74dc
|
[Realtime] Add Qwen3-ASR realtime streaming support (#34613)
Signed-off-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
|
2026-02-20 19:59:42 -08:00 |
|
|
Lucas Wilkinson
|
0e22cd618b
|
Revert "[Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers " (#34997)
|
2026-02-20 17:19:19 -08:00 |
|
|
Wei ZhaoandCyrus Leung
|
ea5f903f80
|
Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-02-20 13:37:31 -08:00 |
|
|
|
ea37530b47
|
[Models] LFM2: Support LoRA (#34921)
Co-authored-by: Piotr Mazurek <piotr635@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-02-19 22:07:23 -08:00 |
|
|
Wentao Ye
|
c683d11c94
|
[Refactor] Deprecate head_first for chunk_gated_delta_rule (#34263)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-02-19 13:23:49 -05:00 |
|
|
roikoren755andMichael Goin
|
3eff45d793
|
Revert "[NemotronH] Do not force router to run in fp32 (#34582)" (#34808)
Signed-off-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-19 09:47:05 -08:00 |
|
|
Robert ShawandRobert Shaw
|
4685a630a2
|
[Model Bash][DeepSeekR1] Remove Shared Expert Clone (#34344)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-02-19 07:56:14 -08:00 |
|
|
|
ee1d25f199
|
[Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers (#34471)
Signed-off-by: Your Name <you@example.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-02-19 07:55:41 -08:00 |
|
|
Linda
|
6fff24f30f
|
[Bugfix] Qwen3.5 kv-scale weight remapping (#34719)
Signed-off-by: Linda-Stadter <57756729+Linda-Stadter@users.noreply.github.com>
|
2026-02-19 04:13:37 -08:00 |
|
|
Tal NirandClaude Opus 4.6
|
f75b61a9e9
|
[Voxtral Realtime] Fix engine crash on empty multimodal embeddings (#34862)
Signed-off-by: Tal Nir <tal@nervexneurotech.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-02-18 23:21:47 -08:00 |
|
|
Wei Zhao
|
7f51e93864
|
[Bug] Fix DeepSeek V3 weight loading caused by incorrect prefix (#34876)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-18 23:20:30 -08:00 |
|
|
Alex Brooks
|
4611af1663
|
[Bugfix] Add Quant Config to Llava Next Projector (#34847)
Signed-off-by: Alex Brooks <albrooks@redhat.com>
|
2026-02-18 23:18:23 -08:00 |
|
|
Manrique Vargas
|
ad5aa6bd9f
|
fix(docs): fix typos in comments and docstrings (#34836)
Signed-off-by: machov <mv1742@nyu.edu>
|
2026-02-18 23:17:41 -08:00 |
|
|
Isotr0pyandJJJYmmm
|
c0bd8b13da
|
[Bugfix] Redo Qwen3.5/Qwen3-Next GDN projector fusion (#34697)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com>
|
2026-02-18 09:46:53 -08:00 |
|
|
Robert ShawandRobert Shaw
|
6874638bc4
|
[Model Bash] DeepSeek R1 BF16 Min Latency QKV A GEMM (0.5% E2E Speedup) (#34758)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
|
2026-02-18 07:42:36 -08:00 |
|
|
Michael Goin
|
909b147197
|
[Bugfix] Fix prefix creation for Qwen3.5 (#34723)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-02-17 23:39:15 -08:00 |
|
|
Cyrus Leung
|
a0d8d944e2
|
[Renderer] Move MM Hash parsing into Renderer (#34711)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-02-17 19:18:55 -08:00 |
|
|
Cyrus Leung
|
574fe75245
|
[Renderer] Move InputPreprocessor into Renderer (2/2) (#34560)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-02-17 05:29:01 -08:00 |
|
|
Jiangyun Zhu
|
1d65283e95
|
Revert "[Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj" (#34683)
|
2026-02-17 01:29:27 -08:00 |
|
|
roikoren755
|
3b30e61507
|
[NemotronH] Do not force router to run in fp32 (#34582)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-02-16 10:15:32 -08:00 |
|
|
Andreas Karatzas
|
03a8770a6d
|
[ROCm][CI] Fix plugins test group; updating terratorch and dependencies (#34589)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-02-16 07:33:42 -08:00 |
|
|
Isotr0py
|
3bb4e4311c
|
[Models] Fuse Qwen3.5 GDN's qkvz_proj and ba_proj (#34492)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-02-16 07:32:51 -08:00 |
|
|
Cyrus Leung
|
ec17bdd894
|
[Renderer] Move InputPreprocessor into Renderer (1.5/2) (#34598)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
|
2026-02-15 23:46:33 -08:00 |
|
|
Isotr0py
|
91ac5d9bfd
|
[CI/Build] Enable tests for recent day-0 new models (#34585)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-02-15 18:17:04 -08:00 |
|
|
Luka Govedičandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
23d825aba1
|
[torch.compile] Disable ar-rms fusion for ds3-fp4 & DP, fix CI test (#34392)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-02-15 06:33:57 -08:00 |
|
|
Isotr0py
|
71cd89264f
|
[MM Encoder] Add Triton ViT attention backend (#32183)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-02-15 06:32:47 -08:00 |
|
|
Cyrus Leung
|
73391a1baa
|
[Renderer] Move InputPreprocessor into Renderer (1/2) (#34510)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2026-02-14 10:14:21 -08:00 |
|
|
Kata Coder
|
d1ea65d0a1
|
[new model] add COLQwen3 code & Inference (#34398)
Signed-off-by: craftsangjae <craftsangjae@gmail.com>
Signed-off-by: katacoder <craftsangjae@gmail.com>
|
2026-02-14 12:15:19 +08:00 |
|
|
Andreas Karatzas
|
de42abb366
|
[CI] Heavy refactoring of Voxtral multimodal audio model tests (#34294)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-02-13 20:04:29 -08:00 |
|
|
Wei Zhao
|
b37b679770
|
[Feature][Perf] Support Selective CPU Weight Offloading (#34535)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-13 20:02:24 -08:00 |
|
|
Harry Huang
|
c027541eaf
|
[Hybrid] Enable spec decoding in mamba cache align mode (#33705)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
|
2026-02-13 13:02:28 -08:00 |
|
|
Wei ZhaoandMichael Goin
|
59d53066d8
|
[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-13 08:11:26 -08:00 |
|
|
LoganJaneandIsotr0py
|
4a9952ec1b
|
[Bugfix] Add quant_config in ViT of Kimi-K2.5 (#34501)
Signed-off-by: LoganJane <LoganJane73@hotmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-02-13 16:05:34 +00:00 |
|