|
c245d35ff4
|
[Model] Add MiMo-V2.5 support (#40967)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: zjy0516 <zhujiangyun@inferact.ai>
Co-authored-by: yasong <yasong.wang@inferact.ai>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Copilot <copilot@github.com>
|
2026-04-27 13:26:51 +00:00 |
|
|
Xiaoshuang Wangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
f8ac0c7cf0
|
[Bugfix] Fix k_norm weight sharding in MiniMaxM2Attention when total_num_kv_heads < tp_size (#38191)
Signed-off-by: wxsIcey <1790571317@qq.com>
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-27 05:57:13 -07:00 |
|
|
Yongye Zhu
|
706a04d34b
|
[DSV4] Add silu clamp limit to shared expert (#40950)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-04-27 00:37:43 -07:00 |
|
|
Isotr0py
|
22631f80a0
|
[Bugfix] Remove invalid deepstack boundary check for Qwen3-VL (#40932)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-04-27 07:27:06 +00:00 |
|
|
Zhanda ZhuandYubo Gao
|
5d5c776444
|
[Perf] FP8 FlashInfer Attn for ViT (#38065)
Signed-off-by: Zhanda Zhu <zhandazhu@gmail.com>
Co-authored-by: Yubo Gao <ybgao-nvidia@users.noreply.github.com>
|
2026-04-27 13:44:15 +08:00 |
|
|
+7
|
4d51588e23
|
[Feat] DeepSeek V4 Rebased (#40860)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: qizixi <zixi@inferact.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Yongye Zhu <yongye@inferact.ai>
Co-authored-by: Simon Mo <simon@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roy Wang <yasong.wang@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Zhewen Li <jerven.vllm@gmail.com>
Co-authored-by: Zijing Liu <liuzijing2014@gmail.com>
Co-authored-by: khluu <khluu000@gmail.com>
Co-authored-by: qizixi <zixi@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
|
2026-04-26 18:31:08 -07:00 |
|
|
labAxiaoming
|
6646c0c7e0
|
[Opt] Optimize deepstack buffer handling for multimodal Qwen3 models (#40145)
Signed-off-by: xiaoming <1259730330@qq.com>
|
2026-04-25 21:04:26 +08:00 |
|
|
Jiangyun Zhu
|
e8ee2a78db
|
[Attention] use diff kv backend for mimo v2 flash (#40045)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-04-24 11:25:55 +00:00 |
|
|
milesial
|
9ad5abe772
|
Fix Nano Nemotron VL static image inputs (#40724)
Signed-off-by: Alexandre Milesi <milesial@users.noreply.github.com>
|
2026-04-24 09:18:55 +00:00 |
|
|
|
512f522192
|
[Model] Gemma4: add bidirectional vision attention for sliding layers with window guard (#40534)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Signed-off-by: Luciano Martins <lucianomartins@google.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-04-24 08:27:46 +00:00 |
|
|
Hemanth Acharya
|
fa4b70555b
|
[ROCm] Cast score correction bias tensor during model construction for DeepSeek/Kimi-K2 (#39999)
Signed-off-by: Hemanth Acharya <heachary@amd.com>
|
2026-04-24 09:02:12 +09:00 |
|
|
bnellnm
|
1c2c1eb8b9
|
[MoE Refactor] Rename FusedMoE.make_expert_params_mapping to fused_moe_make_expert_params_mapping (#40671)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-04-23 11:22:34 -04:00 |
|
|
stevenkuangandJee Jee Li
|
d0009ddb0b
|
[Model] Support Hy3 preview (#40681)
Signed-off-by: stevenkuang <stevenkuang@tencent.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-04-23 22:08:26 +08:00 |
|
|
Shanshan Shen
|
fe57be7809
|
[MM][CG] Support --enable-vit-cuda-graph option for VLM examples (#40580)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-04-22 22:46:14 -07:00 |
|
|
Kunshang Ji
|
342c58bc54
|
[BugFix]fix Qwen3 MoE call gate twice (#40664)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-04-23 05:04:41 +00:00 |
|
|
AllenDouandzixiao
|
9047288b68
|
support hotwords for FunASR model (#39674)
Signed-off-by: zixiao <shunli.dsl@alibaba-inc.com>
Co-authored-by: zixiao <shunli.dsl@alibaba-inc.com>
|
2026-04-22 02:25:06 -07:00 |
|
|
philip-essential
|
123674879e
|
[Model] Add block-local attention and YaRN for local layers to Gemma3 (#39823)
Signed-off-by: Philip Monk <169196560+philip-essential@users.noreply.github.com>
|
2026-04-21 23:34:50 -07:00 |
|
|
|
4eafc72928
|
[Audio] Bundle get_generation_prompt() params into SpeechToTextParams (#36268)
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2026-04-22 12:24:18 +08:00 |
|
|
bnellnm
|
5e584ce9ec
|
[MoE Refactor] Remove SharedFusedMoE class (#35782)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-04-21 18:12:12 -04:00 |
|
|
Wentao Ye
|
1842447c09
|
[Refactor] Remove unused param (#39750)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-04-21 14:59:20 -07:00 |
|
|
Harry Mellor
|
6ee081d1d0
|
Add new tp plan styles to the Transformers modelling backend (#40467)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-04-21 08:51:30 -07:00 |
|
|
roikoren755
|
f819265a4a
|
Default to 'align' mamba cache mode for Mamba-based models when speculative decoding is enabled (#40454)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-04-21 14:51:43 +00:00 |
|
|
Shanshan Shen
|
936e0b79aa
|
[MM][CG] Optimize default max_frames_per_batch auto-infer for ViT CUDA graph video inference (#40445)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2026-04-21 14:47:53 +00:00 |
|
|
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
|
908a713488
|
[Bugfix] LoRA: extend expert base_layer loading to Qwen3.5 and Step3.x (#37114)
Signed-off-by: Hollow Man <hollowman@opensuse.org>
|
2026-04-21 14:17:03 +00:00 |
|
|
|
d249a9e90e
|
Add Granite 4.1 Vision as built-in multimodal model (#40282)
Signed-off-by: Artem Spector <artems@il.ibm.com>
Signed-off-by: artemspector <artems@il.ibm.com>
Co-authored-by: artemspector <artems@il.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-04-21 05:43:39 -07:00 |
|
|
Luciano MartinsandLuciano Martins
|
20d3743491
|
[Bugfix] Gemma4: fix multimodal embedder norm order to match HF reference (#40411)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-04-21 02:28:26 +00:00 |
|
|
bnellnmandRobert Shaw
|
726efe177b
|
[MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-04-20 12:28:46 -04:00 |
|
|
Julien Denize
|
6097afb9bd
|
[BUGFIX] Fix Pixtral consolidated format vision weight loading (#39916)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
|
2026-04-19 22:25:03 -07:00 |
|
|
TJian
|
45232a454e
|
[FEAT] [Perf] [Gemma4] Fused Gemma4 Routing Function Triton (#39083)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-04-19 09:57:39 +00:00 |
|
|
Rishapveer Singh
|
aeee7ef939
|
[Bugfix] Fix k_proj's bias for GLM-ASR (#40160)
Signed-off-by: Rishapveer Singh <singhrishapveer@gmail.com>
|
2026-04-17 22:34:33 -07:00 |
|
|
allgatherandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
640cc9dd7d
|
feat: Add LoRA support for Gemma4ForConditionalGeneration (#39291)
Signed-off-by: allgather <all2allops@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-04-17 09:39:19 -07:00 |
|
|
Lukas Geiger
|
b1dc87a098
|
[Models][Gemma4] Prevent GPU/CPU sync in embed_input_ids (#39234)
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
|
2026-04-17 12:37:21 +00:00 |
|
|
Netanel Haber
|
c4e601c73c
|
Bugfix: Parakeet: .conv.pointwise/depthwise_conv1/2.bias weigths can exist even if convolution_bias=False (#40007)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
|
2026-04-16 23:22:05 +00:00 |
|
|
grYe99andgrYe99
|
4269b79409
|
[Model] Use mm_features to compute mrope positions for PaddleOCR-VL (#39888)
Signed-off-by: grYe99 <guorongye99@gmail.com>
Co-authored-by: grYe99 <guorongye99@gmail.com>
|
2026-04-16 06:14:00 -07:00 |
|
|
lalit10
|
17d87168d2
|
[Model] Use mm_features for Keye-VL and Keye-1.5-VL M-RoPE (#39869)
Signed-off-by: Lalit Laxminarayan Bangad <lalitbangad@gmail.com>
|
2026-04-16 02:16:06 -07:00 |
|
|
Abhijit Royandwang.yuqi
|
2cdf86044d
|
Add Jina Embeddings v5 model support (fixes #38633) (#39575)
Signed-off-by: Abhijit <abroy@redhat.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-04-16 06:37:10 +00:00 |
|
|
|
03f8d3a548
|
Update to transformers v5 (#30566)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: khluu <khluu000@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: jiang1.li <jiang1.li@intel.com>
|
2026-04-15 16:29:15 -07:00 |
|
|
Luciano MartinsandLuciano Martins
|
6dc9491406
|
[Model] Fix Gemma 4 token repetition by dynamic BOS injection for PT models (#39842)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
|
2026-04-15 16:13:07 -07:00 |
|
|
Collin McCarthy
|
27c0ca50a0
|
Update registry for Nemotron-v3 VL Nano/Super (#39747)
Signed-off-by: Collin McCarthy <cmccarthy@nvidia.com>
|
2026-04-15 16:09:11 -07:00 |
|
|
Benjamin Chislett
|
ac3dac545b
|
[Bugfix][Perf] Indexer upcast WK to BF16 for fusion (#38928)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-04-15 20:39:32 +00:00 |
|
|
zhanqiuhu
|
0b790a2501
|
[Speculative Decoding] Add DFlash speculators config parsing (#38300)
Signed-off-by: Zhanqiu Hu <zhu@redhat.com>
|
2026-04-15 16:22:15 -04:00 |
|
|
danielafrimiandroot
|
8b5531933a
|
FIX: support language_model.backbone naming in NemotronH Nano VL quantization config (#39901)
Signed-off-by: <>
Co-authored-by: root <root@lyris0144.lyris.clusters.nvidia.com>
|
2026-04-15 13:49:48 +00:00 |
|
|
Yan Ma
|
29e5d10205
|
fix online fp8 for MiniCPM models (#39862)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-04-15 09:09:20 +00:00 |
|
|
bnellnm
|
19ec9a0a62
|
[MoE Refactor] Refactor ZeroExpertFusedMoE into new framework (#35549)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-04-14 16:11:20 -04:00 |
|
|
roikoren755
|
ecf5ff7ce3
|
[Mamba] Flashinfer selective_state_update (#36162)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-04-14 15:10:58 -04:00 |
|
|
Hexiang Wang
|
f02b3269e7
|
[PluggableLayer][3/N] Apply PluggableLayer to moe-related layers. (#33556)
Signed-off-by: whx-sjtu <2952154980@qq.com>
|
2026-04-14 09:55:00 -04:00 |
|
|
bhargav-patel-29andgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
f7e62e3d66
|
[Bugfix] Fix mismatch between global and local attention heads in tensor-parallel mode for param2moe model (#39707)
Signed-off-by: bhargav-patel-29 <bhargav.patel@tihiitb.org>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-04-14 20:13:36 +08:00 |
|
|
|
6f786f2c50
|
[Bugfix][Model] Fix Devstral Small 2 HF format weight loading (#39293)
Signed-off-by: thomasmaindron <thomasmaindron@users.noreply.github.com>
Co-authored-by: thomasmaindron <thomasmaindron@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-14 10:11:18 +00:00 |
|
|
Shanshan ShenandRoger Wang
|
80118853f4
|
[MM][Perf][CG] Support ViT full CUDA graph for Qwen3-VL video inference (#38061)
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-04-14 16:49:32 +08:00 |
|
|
lalit10andCyrus Leung
|
0008729abf
|
[Model] Use mm_features for Ernie-4.5 VL M-RoPE (#39753)
Signed-off-by: Lalit Laxminarayan Bangad <lalitbangad@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-04-14 01:11:52 -07:00 |
|