 Woosuk Kwon
|
c733bd5e87
|
[Qwen3-Next] Add MoE Config for H200 (#24688)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
|
2025-09-11 12:40:15 -07:00 |
|
|
Wentao Ye
|
a892b259b4
|
[Doc] Remove Useless Comments (#24687)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-11 12:25:47 -07:00 |
|
|
Peter Salas
|
127ded0a9e
|
[Ultravox] Use wrapped_model_config to instantiate inner model (#24679)
Signed-off-by: Peter Salas <peter@fixie.ai>
|
2025-09-11 18:52:24 +00:00 |
|
|
Isotr0py
|
bb2b5126da
|
[VLM] Migrate remain DP-supported ViT models to use disable_tp (#24363)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-11 18:30:41 +00:00 |
|
|
co63oc
|
e26fef8397
|
fix some typos (#24616)
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
|
2025-09-11 10:48:46 -07:00 |
|
|
Konrad Zawora
|
4aa23892d6
|
[Bugfix] Fix platform-specific routing in CustomOp implementations (#24444)
Signed-off-by: Konrad Zawora <kzawora@habana.ai>
|
2025-09-11 17:15:01 +00:00 |
|
|
Isotr0py
|
bcbe2a4d9e
|
[VLM] Optimize GLM4.5-V-style video processing to only decode necessary frames (#24161)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-11 09:44:34 -07:00 |
|
|
Jee Jee Li
|
817beef7f3
|
[Bugifx] Fix qwen-next packed_modules_mapping (#24656)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-11 22:26:17 +08:00 |
|
|
Harry Mellor
|
5f5271f1ee
|
Move LoRAConfig from config/__init__.py to config/lora.py (#24644)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-11 11:01:38 +00:00 |
|
|
Harry Mellor
|
d6249d0699
|
Fix typing for safetensors_load_strategy (#24641)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-11 10:41:39 +00:00 |
|
|
Kyuyeun Kim
|
ed5ae4aace
|
[Bugfix] Fix _synced_weight_loader (#24565)
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
|
2025-09-11 16:52:33 +08:00 |
|
|
Tao HeandJee Jee Li
|
e93f4cc9e3
|
Add the support for the qwen3 next model (a hybrid attention model). (#24526)
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-11 15:32:09 +08:00 |
|
|
Jerry Zhang
|
2048c4e379
|
[torchao] Support quantization configs using module swap (#21982)
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
|
2025-09-10 23:53:24 -07:00 |
|
|
|
d13360183a
|
Remove redundant all gather + split (#23441)
Co-authored-by: Chenxi Yang <cxyang@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
|
2025-09-10 23:45:07 -07:00 |
|
|
|
9bd831f501
|
[Model] New model support for Motif-1-Tiny (#23414)
Signed-off-by: ca1207 <ca1207zzz@gmail.com>
Signed-off-by: TaehyunKim <73943231+ca1207@users.noreply.github.com>
Co-authored-by: WyldeCat <skan1543@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-10 23:29:40 -07:00 |
|
|
Didier Durand
|
e2b1f863aa
|
[Doc]: fixing doc typos (#24635)
Signed-off-by: Didier Durand <durand.didier@gmail.com>
|
2025-09-10 23:19:28 -07:00 |
|
|
shengshiqi-googleandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
41329a0ff9
|
[Core] feat: Add --safetensors-load-strategy flag for faster safetensors loading from Lustre (#24469)
Signed-off-by: Shiqi Sheng <shengshiqi@google.com>
Signed-off-by: shengshiqi-google <160179165+shengshiqi-google@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-09-10 23:10:01 -07:00 |
|
|
Saman A. Pour
|
3d1393f6fc
|
Kimi K2 Fused MoE kernels Optimization configs (#24597)
Signed-off-by: Saman Keon <samanamp@outlook.com>
|
2025-09-10 23:06:16 -07:00 |
|
|
Peter Salas
|
f17a6aa4ec
|
[Ultravox] Fix Gemma instantiation, support quantization via --hf-overrides (#24131)
Signed-off-by: Peter Salas <peter@fixie.ai>
|
2025-09-10 22:25:34 -07:00 |
|
|
|
5931b7e5d9
|
[Models][Quantization] Add quantization configuration update in Voxtral model (#24122)
Signed-off-by: Alexandre Marques <almarque@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-09-10 19:13:56 -07:00 |
|
|
|
fba7856581
|
[Perf] Warmup FlashInfer attention during startup (#23439)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni001@gmail.com>
|
2025-09-10 15:03:17 -07:00 |
|
|
|
9a161307f5
|
[torch.compile][ROCm][V1] Enable attention output FP8 fusion for V1 attention backends (#19767)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
|
2025-09-10 13:59:55 -07:00 |
|
|
Russell BryantandNickLucche
|
37e8182bfe
|
[v1] Add Whisper model support (encoder-decoder) (#21088)
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
|
2025-09-10 13:53:35 -07:00 |
|
|
Ming Yang
|
4032949630
|
[Bugfix] Fix DeepEP config for DP4TP4 (#23619)
Signed-off-by: Ming Yang <minos.future@gmail.com>
|
2025-09-10 10:37:56 -07:00 |
|
|
tomeras91andCyrus Leung
|
08abfa78ec
|
[Bugfix] fix modelopt exclude_modules name mapping (#24178)
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-09-10 10:20:46 -07:00 |
|
|
zzhxxx
|
736569da8d
|
[Platform] Custom ops support for LMhead and LogitsProcessor (#23564)
Signed-off-by: zzhx1 <zzh_201018@outlook.com>
|
2025-09-10 06:26:31 -07:00 |
|
|
|
ccee371e86
|
[Docs] Fix warnings in mkdocs build (continued) (#24092)
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-09-10 06:23:28 -07:00 |
|
|
RoadToNowhereXandWentao Ye
|
c0bd6a684a
|
Fix Auto_Round Quatization Loading on SM75 and Lower GPUs (#24217)
Signed-off-by: RoadToNowhereX <37441177+RoadToNowhereX@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2025-09-10 06:22:31 -07:00 |
|
|
Wenlong Wang
|
4c04eef706
|
[BugFix][Multi Modal] Fix TensorSchema shape mismatch in Molmo (#24559)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
|
2025-09-10 06:14:27 -07:00 |
|
|
Harry Mellor
|
f36355abfd
|
Move LoadConfig from config/__init__.py to config/load.py (#24566)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-10 06:14:18 -07:00 |
|
|
Yash Pratap SinghandJee Jee Li
|
9e3c3a7df2
|
[LoRA]: Add LoRA support to Mistral's Voxtral models (#24517)
Signed-off-by: Yash Pratap Singh <yashsingh20001@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-10 06:12:03 -07:00 |
|
|
baonudesifeizhaiandIsotr0py
|
6cbd41909e
|
Feature/vit attention unification# 23880 (#23978)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-10 06:10:14 -07:00 |
|
|
danielafrimi
|
72d30108a0
|
Support for NemotronH Nano VLM (#23644)
Signed-off-by: Daniel Afrimi <danielafrimi8@gmail.com>
|
2025-09-10 06:10:06 -07:00 |
|
|
vllmellm
|
7c195d43da
|
[ROCm][Bugfix] Fix Aiter RMSNorm (#23412)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
|
2025-09-10 21:08:03 +08:00 |
|
|
li-jinpengandRoger Wang
|
267c80d31f
|
[Model] Limit CPU threads for image transformations in InternVL to reduce cpu contention. (#24519)
Signed-off-by: li-jinpeng <3332126450@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2025-09-10 16:45:44 +08:00 |
|
|
|
4377b1ae3b
|
[Bugfix] Update Run:AI Model Streamer Loading Integration (#23845)
Signed-off-by: Omer Dayan (SW-GPU) <omer@run.ai>
Signed-off-by: Peter Schuurman <psch@google.com>
Co-authored-by: Omer Dayan (SW-GPU) <omer@run.ai>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-09-09 21:37:17 -07:00 |
|
|
Chenheli Hua
|
009d689b0c
|
[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
|
2025-09-09 21:36:09 -07:00 |
|
|
Wei
|
0efdb5c3ba
|
[gpt-oss] Cache permute indices for faster MXFP4 MoE layer loading (#24154)
Signed-off-by: Wei Wei <wwei6@meta.com>
|
2025-09-10 04:27:53 +00:00 |
|
|
Wenlong Wang
|
53b42f4102
|
[BugFix][Spec Decode] Fix out-of-range index triggered by eagle3; re-enable test for LlamaForCausalLMEagle3 (#24392)
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
|
2025-09-09 21:24:23 -07:00 |
|
|
bnellnm
|
b23fb78623
|
[Bugfix] Fix for 24530. Fix naive all2all shared expert overlap. (#24538)
|
2025-09-09 17:53:53 -07:00 |
|
|
Jee Jee Li
|
9ad0688e43
|
[Bugfix] Fix hidden_size for multimodal classification model (#24501)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-09 10:37:25 -07:00 |
|
|
youkaichao
|
1aa427fdc1
|
[Kernels] Add Flash Linear Attention Kernels (#24518)
Signed-off-by: youkaichao <youkaichao@gmail.com>
|
2025-09-10 00:04:41 +08:00 |
|
|
wang.yuqi
|
19332c0479
|
[Model] Systematic support for fp32 head, pooling models part (#23810)
Signed-off-by: wang.yuqi <noooop@126.com>
|
2025-09-09 07:29:50 -07:00 |
|
|
WeiQing ChenandJunhong
|
e283976f3a
|
[Performance][MM] Building the inverse permutation in O(n) time in Qwen2_5_VisionTransformer (#24443)
Signed-off-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: Junhong <liujunhong11@huawei.com>
|
2025-09-09 00:24:11 -07:00 |
|
|
CSWYF3634076
|
b6fbc15634
|
[BugFix][Model] Fix Ernie4.5-VL hanging on long inputs (#24074)
Signed-off-by: wangyafeng <wangyafeng@baidu.com>
|
2025-09-09 11:37:16 +08:00 |
|
|
Tyler Michael Smith
|
955c624915
|
[Bugfix][Wide EP] Fix redundant work when using DeepEP, TP Attn, and EP MoE (#24134)
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2025-09-08 19:01:51 -07:00 |
|
|
Yang KaiyongandSimon Mo
|
43d9ad03ba
|
[Model loader]: support multi-thread model weight loading (#23928)
Signed-off-by: Yang Kaiyong <yangkaiyong.yky@antgroup.com>
Signed-off-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
|
2025-09-08 18:49:39 +00:00 |
|
|
Jee Jee Li
|
8d7f39b48c
|
[Model] Remove quantized mixtral (#24437)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-08 11:02:14 -07:00 |
|
|
Jee Jee Li
|
6f4a82f8b5
|
[Model] Enable BNB support for qwen2_5_omni_thinker (#24420)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-08 09:37:08 -07:00 |
|
|
|
01dfb5e982
|
[Frontend] User-provided uuids for medias in chat. (RFC #22044) (#23449)
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
|
2025-09-08 06:42:20 -07:00 |
|