Commits · 993c31c3c0a939f7a9832ccaa97a09efd024b929 · OpenDAS / vllm_cscc

08 Jan, 2026 1 commit
- update dispatch_unquantized_gemm · 993c31c3
  zhuwenwen authored Jan 08, 2026
  
  993c31c3
03 Oct, 2025 2 commits
- update deepseek_v2.py · 10bca78b
  zhuwenwen authored Oct 03, 2025
  
  10bca78b
- skip load index weights error · b79e20fe
  zhuwenwen authored Oct 03, 2025
  
  b79e20fe
02 Oct, 2025 2 commits
- [Deepseek v3.2] Support indexer prefill chunking (#25999) · c75c2e70
  Chen Zhang authored Oct 02, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  c75c2e70
- skip is_v32 · 4b26fd42
  zhuwenwen authored Oct 02, 2025
  
  4b26fd42
01 Oct, 2025 7 commits

update fused_moe.py · 241ea5cd
zhuwenwen authored Oct 02, 2025

241ea5cd
skip is_v32 · 1faf662d
zhuwenwen authored Oct 02, 2025

1faf662d
[BugFix] Fix default kv-cache-dtype default for DeepseekV3.2 (#25988) · e4beabd2
Lucas Wilkinson authored Oct 01, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
e4beabd2
[MM] Add text-only mode for Qwen3-VL (#26000) · a1825fe6
Roger Wang authored Sep 30, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
a1825fe6

[New Model] DeepSeek-V3.2 (Rebased to Main) (#25896) · b3230e1a

Yongye Zhu authored Sep 30, 2025


Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

b3230e1a

[Bug] Fix Weight Loading for Block FP8 Cutlass SM90 (#25909) · 9471879b

Wentao Ye authored Sep 29, 2025

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

9471879b

[Bugfix] Fallback ViT attn backend to SDPA for blackwell (#25851) · ab5b6459
Roger Wang authored Sep 28, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
ab5b6459

29 Sep, 2025 1 commit

[Bugfix] fix Qwen3VLMoe load when pp > 1 (#25838) · 09c2cbc0

JJJYmmm authored Sep 29, 2025


Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
Signed-off-by: simon-mo <simon.mo@hey.com>

09c2cbc0

28 Sep, 2025 4 commits
- [VLM] Update Qwen3-VL max_num_video_tokens calculation for configurable video profiling (#25557) · 4c347044
  Isotr0py authored Sep 28, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  4c347044
- [Bugfix] Fix Qwen3-VL regression from #24982 (#25814) · 19e7ab73
  Roger Wang authored Sep 27, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  19e7ab73
- [Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982) · 26a7a33b
  Tyler Michael Smith authored Sep 27, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  26a7a33b
- [Bugfix] Allow Only SDPA Backend for ViT on B200 for Qwen3-VL (#25788) · c2fa2d4d
  Wentao Ye authored Sep 26, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  c2fa2d4d
26 Sep, 2025 9 commits

Eagle3 that supports the Minicpm3 model (#24243) · 33f6aaf9

阿丹(adan) authored Sep 27, 2025


Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: liudan <adan@minicpm.com>
Co-authored-by: liudan <liudan@qq.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>

33f6aaf9

[Quantization] Add field to skip unquantized modules for GPTQ config (#25455) · d4d98998
Isotr0py authored Sep 26, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
d4d98998

[Model] Mamba2 varlen refactor (#21467) · 2b6b1d78

Chih-Chieh Yang authored Sep 26, 2025


Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: RishiAstra <40644327+RishiAstra@users.noreply.github.com>

2b6b1d78

[Bugfix] Fix Shared Expert/Zero expert code in FusedMoE.process_chunk (#25698) · dfb9af20

Sage Moore authored Sep 26, 2025


Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

dfb9af20

[Qwen3-Next][GDN] fixes cuda graph capturing bug in GDN metadata and a stride... · 99b3a504

Tao He authored Sep 26, 2025


[Qwen3-Next][GDN] fixes cuda graph capturing bug in GDN metadata and a stride bug in causal_conv_1d. (#25743)
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>

99b3a504

[Harware][AMD][Model] Triton MoE tuning configs for GLM-4.5 for MI300X (#25703) · 52621c8f
xaguilar-amd authored Sep 26, 2025
```
Signed-off-by: xaguilar <Xavier.AguilarFruto@amd.com>
```
52621c8f

EVS Support (Video tokens pruning) (#22980) · 392edee3

Eugene Khvedchenya authored Sep 26, 2025


Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com>
Signed-off-by: Eugene Khvedchenya <ekhvedchenya@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

392edee3

Llamas 3.1 405B fp4 changes upstreaming from 355_wip (#25135) · 53a30845

Aleksandr Malyshev authored Sep 25, 2025


Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>

53a30845

[Refactor] Remove DeepGEMM OP Register (#25710) · 9fe4c2bd
Wentao Ye authored Sep 25, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
9fe4c2bd

25 Sep, 2025 14 commits
- Fix routing_bias dtype (#25711) · 081b5594
  Shu Wang authored Sep 25, 2025
```
Signed-off-by: Shu Wang. <shuw@nvidia.com>
```
  081b5594
- [Model] rename NemotronH_Nano_VL -> NemotronH_Nano_VL_V2 (#25708) · 57329a8c
  tomeras91 authored Sep 26, 2025
```
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
```
  57329a8c
- [Optimization] Use a cheaper cache key in `get_model_architecture` (#25682) · 89fa54e6
  Cyrus Leung authored Sep 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  89fa54e6
- [V0 deprecation] Remove _VLLM_V1 suffixes from attention backend names (#25489) · 3468f17e
  Matthew Bonanni authored Sep 25, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
  3468f17e
- [Model] Define `merge_by_field_config` MM interface (#25676) · 0ea80c87
  Cyrus Leung authored Sep 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  0ea80c87
- Revert "[Bug] Dynamo Unsupported due to `BasevLLMParameter.torch_function`... · 916bd920
  Michael Goin authored Sep 25, 2025
```
Revert "[Bug] Dynamo Unsupported due to `BasevLLMParameter.torch_function` calling disabled super()" (#25681)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  916bd920
- [Bugfix] Fix InternS1 video processing after Transformers v4.56 (#25644) · 03858e6d
  Isotr0py authored Sep 25, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  03858e6d
- [mypy] Further improve MM type annotations (#25654) · 12c1287d
  Cyrus Leung authored Sep 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  12c1287d
- [Bugfix] Fix Qwen3-VL max_num_video_tokens calculation for video profiling (#25648) · 17b4c668
  Isotr0py authored Sep 25, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  17b4c668
- [Misc] Fix Qwen3-VL `video_grid_thw` typing (#25646) · 7be9ffcd
  Roger Wang authored Sep 25, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  7be9ffcd
- Revert "[Performance] Move apply_w8a8_block_fp8_linear to an op class… (#25607) · 1260180c
  Tyler Michael Smith authored Sep 25, 2025
```
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
  1260180c
- Map CwmForCausalLM to llama and LlamaForCausalLM (#25611) · bc092ea8
  Jacob Kahn authored Sep 25, 2025
```
Signed-off-by: Jacob Kahn <jacobkahn1@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  bc092ea8
- [Misc] Simplify PoolerOutput and move to `v1/outputs` (#25629) · 755ed7b0
  Cyrus Leung authored Sep 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  755ed7b0
- [Model] Add LongCat-Flash (#23991) · 845adb3e
  XuruiYang authored Sep 25, 2025
```
Signed-off-by: yangxurui <yangxurui@meituan.com>
Co-authored-by: yangxurui <yangxurui@meituan.com>
```
  845adb3e