Commits · 304dcdf5758fdbf0252966b6b0791bbba9254feb · OpenDAS / vllm_cscc · GitLab

28 Jul, 2025 10 commits
- Migrate GLMVImagePixelInputs to TensorSchema (#21679) · 304dcdf5
  Benji Beck authored Jul 27, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  304dcdf5
- Migrate Glm4vImageInputs, Glm4vVideoInputs to TensorSchema (#21678) · 88e46c7c
  Benji Beck authored Jul 27, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  88e46c7c
- Migrate Gemma3ImagePixelInputs to TensorSchema (#21676) · d8937de4
  Benji Beck authored Jul 27, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  d8937de4
- [FEAT] [ROCm] [AITER]: Add AITER HIP block quant kernel (#21242) · e626d286
  TJian authored Jul 27, 2025
  
  e626d286
- [Model] Support TP/PP/mamba2 kernel for PLaMo2 (#19674) · c7ffe93d
  Shinichi Hemmi authored Jul 28, 2025
```
Signed-off-by: Shinichi Hemmi <shemmi@preferred.jp>
Signed-off-by: Shinichi Hemmi <50256998+Alnusjaponica@users.noreply.github.com>
Co-authored-by: Calvin Metzger <metzger@preferred.jp>
Co-authored-by: Sixue Wang <cecilwang@preferred.jp>
```
  c7ffe93d
- [V1] Exception Handling when Loading KV Cache from Remote Store (#21534) · 15a72ac4
  Adeline authored Jul 28, 2025
```
Signed-off-by: liuyumoye <adeline_ly2023@outlook.com>
Co-authored-by: liuyumoye <adeline_ly2023@outlook.com>
```
  15a72ac4
- [Misc] Add fused_moe configs for Qwen3-Coder-480B-A35B-Instruct-FP8 (#21700) · 04ff4be3
  Jee Jee Li authored Jul 28, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  04ff4be3
- Fix GLM tool parser (#21668) · 93269bb4
  Yuxuan Zhang authored Jul 28, 2025
```
Co-authored-by: Chenhui Zhang <zhang.chenhui@outlook.com>
```
  93269bb4
- Fix typo for limit-mm-per-prompt in docs (#21697) · 82acf218
  Joachim Studnia authored Jul 27, 2025
```
Signed-off-by: Joachim Studnia <joachim@mistral.ai>
```
  82acf218
- [Deprecation][2/N] Replace `--task` with `--runner` and `--convert` (#21470) · 86ae693f
  Cyrus Leung authored Jul 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  86ae693f
27 Jul, 2025 15 commits
- [Attention] Make CutlassMLA the default backend for SM100 (blackwell) (#21626) · 8f605ee3
  Alexander Matveev authored Jul 27, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  8f605ee3
- [Misc] Refactor vllm config str (#21666) · a9b2a1d7
  Ning Xie authored Jul 28, 2025
  
  a9b2a1d7
- Fix CUDA permute/unpermute for use with DeepGemm Moe (#17934) · 57c22e57
  Caleb_Du authored Jul 27, 2025
```
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
```
  57c22e57
- [Refactor] Refactor MOE NVFP4 Code Base: ModelOpt + Compressed Tensor (#21631) · bda9d053
  Wentao Ye authored Jul 27, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  bda9d053
- [VLM] Add video support for Intern-S1 (#21671) · 3d847a31
  Isotr0py authored Jul 27, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3d847a31
- Migrate Florence2ImagePixelInputs to TensorSchema (#21663) · 5f8c9a42
  Benji Beck authored Jul 27, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  5f8c9a42
- [Misc] add default value for file pattern arg (#21659) · 1cbf951b
  Ning Xie authored Jul 27, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  1cbf951b
- Refactor: Remove numpy dependency from LoggingStatLogger (#20529) · a8936e51
  ZiTian.Zhao authored Jul 27, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
```
  a8936e51
- [CI/Build][Doc] Clean up more docs that point to old bench scripts (#21667) · 01a395e9
  Ye (Charlotte) Qi authored Jul 26, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  01a395e9
- Handle non-serializable objects in vllm bench (#21665) · 971948b8
  Huy Do authored Jul 26, 2025
  
  971948b8
- [VLM] Support HF format Phi-4-MM model (#17121) · eed2f463
  Isotr0py authored Jul 27, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  eed2f463
- Migrate ChameleonImagePixelInputs to TensorSchema (#21657) · 20950b29
  Benji Beck authored Jul 26, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  20950b29
- Migrate FuyuImagePatchInputs to TensorSchema (#21662) · 3339cba3
  Benji Beck authored Jul 26, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  3339cba3
- Migrate DeepseekVL2ImageInputs to TensorSchema (#21658) · 0b8caf90
  Benji Beck authored Jul 26, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  0b8caf90
- Migrate Blip2ImagePixelInputs and Blip2ImageEmbeddingInputs to TensorSchema (#21656) · ccf27cc4
  Benji Beck authored Jul 26, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  ccf27cc4
26 Jul, 2025 15 commits
- support `torch.compile` for bailing moe (#21664) · c6573698
  Jinzhen Lin authored Jul 27, 2025
  
  c6573698
- Remove xformers requirement for Mistral-format Pixtral and Mistral3 (#21154) · 6c66f28f
  Wenchen Lo authored Jul 26, 2025
```
Signed-off-by: Wenchen Lo <charles761013@gmail.com>
```
  6c66f28f
- [NVIDIA] Explicitly disable shuffled weights for flashinfer blockscale moe fp8 kernels (#21411) · de509ae8
  Kaixi Hou authored Jul 26, 2025
```
Signed-off-by: kaixih <kaixih@nvidia.com>
```
  de509ae8
- [CI/Build][Doc] Move existing benchmark scripts in CI/document/example to vllm bench CLI (#21355) · e7c4f9ee
  Ye (Charlotte) Qi authored Jul 26, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  e7c4f9ee
- [Bugfix][Apple Silicon] fix missing symbols when build from source on Mac with... · 9094d11c
  Yeju Zhou authored Jul 26, 2025
```
[Bugfix][Apple Silicon] fix missing symbols when build from source on Mac with Apple Silicon (#21380)
Signed-off-by: Yeju Zhou <yejuzhou@outlook.com>
```
  9094d11c
- [Refactor] Remove `moe_align_block_size_triton` (#21335) · 56e544f2
  Wentao Ye authored Jul 26, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  56e544f2
- [BugFix] Fix shared storage connector load kv only load attention layer (#21428) · 97d6c30c
  WeiQing Chen authored Jul 26, 2025
```
Signed-off-by: David Chen <530634352@qq.com>
```
  97d6c30c
- [Misc] Improve memory profiling debug message (#21429) · a40a8506
  Ye (Charlotte) Qi authored Jul 26, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  a40a8506
- [Bug] Fix `has_flashinfer_moe` Import Error when it is not installed (#21634) · c215f5c8
  Wentao Ye authored Jul 26, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c215f5c8
- Support encoder-only models without KV-Cache (#21270) · 1cd6eaba
  Maximilien de Bayser authored Jul 26, 2025
```
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
```
  1cd6eaba
- [Bugfix] Investigate Qwen2-VL failing test (#21527) · f27fdfc3
  Isotr0py authored Jul 26, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  f27fdfc3
- Migrate AyaVisionImagePixelInputs to TensorSchema for shape validation (#21622) · de10ff0b
  Benji Beck authored Jul 26, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  de10ff0b
- Migrate AriaImagePixelInputs to TensorSchema for shape validation (#21620) · 9d197280
  Benji Beck authored Jul 26, 2025
```
Signed-off-by: Benji Beck <benjibeck@meta.com>
```
  9d197280
- [Take 2] Correctly kill vLLM processes after benchmarks (#21646) · e98def43
  Huy Do authored Jul 26, 2025
```
Signed-off-by: Huy Do <huydhn@gmail.com>
```
  e98def43
- [Misc] remove unused try-except in pooling config check (#21618) · 05c1126f
  Reid authored Jul 26, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
```
  05c1126f