Commits · a02a1c83b33a6fee7424530d2a1f22a0e753044c · OpenDAS / vllm_cscc

"csrc/vscode:/vscode.git/clone" did not exist on "f6a1053ce59cd25552d5683225a104013c602afd"

11 Sep, 2025 3 commits
- remove redundant routed_scaling_factor · a02a1c83
  zhuwenwen authored Sep 11, 2025
  
  a02a1c83
- remove unused code · a053add9
  zhuwenwen authored Sep 11, 2025
  
  a053add9
- fix: w4a8 marlin 中 weight重排接入lightop算子 · 4f6c0cd4
  zhuwenwen authored Sep 11, 2025
  
  4f6c0cd4
10 Sep, 2025 2 commits
- update awq_marlin.py · 533af8ef
  zhuwenwen authored Sep 10, 2025
  
  533af8ef
- update flash-attn interface of apply_rotary_emb · 6c0a30bc
  zhuwenwen authored Sep 10, 2025
  
  6c0a30bc
04 Sep, 2025 1 commit
- add glm-4.5-air-tp8 nn moe configs · 81301303
  zhuwenwen authored Sep 04, 2025
  
  81301303
03 Sep, 2025 1 commit
- [fix]fix tests of v1 and worker · b2d58051
  zhuwenwen authored Sep 03, 2025
  
  b2d58051
02 Sep, 2025 1 commit
- [fix]fix tests of kernels · af7b564d
  zhuwenwen authored Sep 02, 2025
  
  af7b564d
01 Sep, 2025 4 commits

Migrate Phi4 inputs to TensorSchema (#23471) · 437c3ce0
Benji Beck authored Aug 31, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
437c3ce0
[CI/Build] Improve Tensor Schema tests speed by avoid engine core initialization (#23357) · ff0e59d8
Isotr0py authored Sep 01, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
ff0e59d8

Jun-Howie authored Sep 01, 2025


Signed-off-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: JunHowie <JunHowie@aliyun.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

acc1a6e1

[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and... · 183a7096

JartX authored Sep 01, 2025


[BUGFIX] GPTQ quantization compatibility for Qwen3 MOE models (AutoGPTQ and AutoRound-GPTQ) (#23994)
Signed-off-by: JartX <sagformas@epdcenter.es>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

183a7096

30 Aug, 2025 4 commits

Add LoRA support for DeepSeek models (V2, V3, R1-0528) (#23971) · 379ea282

sadegh.shokatian authored Aug 30, 2025


Signed-off-by: sadeghja1070 <sadegh.ja1070@gmail.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

379ea282

[Model] Enable encoder DP for MiniCPM-V (#23948) · 3a6acad4

Jiangyun Zhu authored Aug 30, 2025


Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

3a6acad4

[V1] [Hybrid] Move MiniMaxLinearAttention into layers/mamba (#23831) · 4071c76c
Thomas Parnell authored Aug 30, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
4071c76c

Add routed_scaling_factor to MoE grouped topk (#23123) · 8fb85b7b

Xin Yang authored Aug 29, 2025


Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

8fb85b7b

29 Aug, 2025 15 commits
- [Misc] Make `download_weights_from_hf` more reliable (#23863) · 5674a403
  Harry Mellor authored Aug 29, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  5674a403
- Revert gemma3n fast prefill changes (#23897) · 8c3e1999
  Yong Hoon Shin authored Aug 29, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  8c3e1999
- Tuned H100/H200 triton fp8 block configs for fused_qkv_a_proj (#23939) · b7adf94c
  Michael Goin authored Aug 29, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  b7adf94c
- [Models] Use in-place adds in Idefics2Vision (#23932) · 0a2f4c07
  Lukas Geiger authored Aug 29, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  0a2f4c07
- [MODEL] `Apertus` and `XIELU` (#23068) · 1cf3753b
  EduardDurech authored Aug 29, 2025
```
Signed-off-by: EduardDurech <39579228+EduardDurech@users.noreply.github.com>
Co-authored-by: AllenHaoHuang <allenhuangdd@gmail.com>
```
  1cf3753b
- [Performance] V1 Classify Models E2E Performance Optimization (#23541) · d9e00dbd
  wang.yuqi authored Aug 29, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  d9e00dbd
- 修复residual FP16 overflow，解决mtp采样率和数据集精度的冲突 · 0369a0a6
  zhuwenwen authored Aug 29, 2025
  
  0369a0a6
- [V0 Deprecation] Remove pooling model support in V0 (#23434) · 2554b27b
  Maximilien de Bayser authored Aug 29, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2554b27b
- Better errors for Transformers backend missing features (#23759) · 934bebf1
  Harry Mellor authored Aug 29, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  934bebf1
- [Misc] Fix warnings for mistral model (#23552) · 885ca6d3
  Jiangyun Zhu authored Aug 29, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  885ca6d3
- [mrope][Qwen2-VL] Fix edge case where getting index of image/video token can... · 2d0afcc9
  Chenheli Hua authored Aug 28, 2025
```
[mrope][Qwen2-VL] Fix edge case where getting index of image/video token can potentially throw in default vl mrope implementation.  (#23895)
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
```
  2d0afcc9
- [BugFix][AMD][Deepseek] fix a dtype mismatch error for deepseek running on AMD (#23864) · 5264015d
  Jinghui Zhang authored Aug 28, 2025
```
Signed-off-by: Jinghui Zhang <jinghuizhang0804@gmail.com>
```
  5264015d
- [Bugfix] Use `ReplicatedLinear` for SequenceClassification head (#23836) · 98ac0cb3
  Isotr0py authored Aug 29, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  98ac0cb3
- [Models] Improve iteration over layers (#19497) · de533ab2
  Lukas Geiger authored Aug 29, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  de533ab2
- [XPU] support data parallel for MoE models on XPU (#22887) · 235c9db8
  Chaojun Zhang authored Aug 29, 2025
```
Signed-off-by: chzhang <chaojun.zhang@intel.com>
```
  235c9db8
28 Aug, 2025 9 commits
- [V1] Enable prefill optimization for Gemma3n (#22628) · cb293f6a
  Yong Hoon Shin authored Aug 28, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  cb293f6a
- [NVIDIA] Support SiluMul + NVFP4 quant fusion (#23671) · 16a45b3a
  elvischenv authored Aug 29, 2025
```
Signed-off-by: jindih <jindih@nvidia.com>
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: jindih <jindih@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedic <lgovedic@redhat.com>
```
  16a45b3a
- Migrate Llama4ImagePatchInputs to TensorSchema (#22021) · f32a5bc5
  Benji Beck authored Aug 28, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  f32a5bc5
- [Model][gpt-oss] Support DP+EP for GPT-OSS with FlashInfer trtllm-gen MoE (#23819) · 95089607
  Po-Han Huang (NVIDIA) authored Aug 28, 2025
```
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
```
  95089607
- [Doc]: fix typos in Python scripts (#23828) · d3da2eea
  Didier Durand authored Aug 28, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  d3da2eea
- [Model] [gpt-oss] fix gpt-oss pp support (#23815) · bfab2196
  Jiangyun Zhu authored Aug 28, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  bfab2196
- [CI/Build][Bugfix] Fix Qwen VL tests on CPU (#23818) · 67cee40d
  Li, Jiang authored Aug 28, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  67cee40d
- [FIXBUG] Add return_success parameter to moe_wna16_weight_loader function (#22797) · 3462c1c5
  JartX authored Aug 28, 2025
```
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  3462c1c5
- [Model] Add PP support and VLM backbone compatability for GPT-OSS (#23680) · c5d004aa
  Isotr0py authored Aug 28, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  c5d004aa