Commits · 77b6e74fe2b6259b2ad4dbca55eca50017a68926 · OpenDAS / vllm_cscc · GitLab

30 May, 2025 3 commits
- [Model] Use AutoWeightsLoader for mamba2 (#18918) · 3987e2ae
  iLeGend authored May 30, 2025
```
Signed-off-by: iLeGend <824040212@qq.com>
```
  3987e2ae
- improve the robustness of parsing vlms config in AutoRound (#18894) · 3de3eadf
  Wenhua Cheng authored May 30, 2025
```
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
```
  3de3eadf
- [Misc] Update type annotation for rotary embedding `base` (#18914) · 1aa2f81b
  Cyrus Leung authored May 30, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  1aa2f81b
29 May, 2025 6 commits
- [TPU] remove transpose ops in moe kernel (#18923) · a1cc9f33
  Chengji Yao authored May 29, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  a1cc9f33
- Fix an error in dummy weight loading for quantization models (#18855) · f8977c23
  Chenyaaang authored May 29, 2025
```
Signed-off-by: Chenyaaang <chenyangli@google.com>
```
  f8977c23
- [LoRA] Add LoRA support for InternVL (#18842) · 34d6c447
  Jee Jee Li authored May 29, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  34d6c447
- [Neuron] Add multi-LoRA support for Neuron. (#18284) · 972eddf7
  Satyajith Chilappagari authored May 29, 2025
```
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
```
  972eddf7
- [Bugfix][TPU] fix moe custom kernel import (#18853) · 8e882ffd
  Chengji Yao authored May 28, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  8e882ffd
- Prevent the cross-encoder logic from being applied to classification tasks (#18838) · 515b413e
  Maximilien de Bayser authored May 28, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  515b413e
28 May, 2025 4 commits
- [Core] Enable CUDA graphs for DP + All2All kernels (#18724) · 7951d787
  Varun Sundar Rabindranath authored May 28, 2025
```
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  7951d787
- [Misc] fix olmoe model layer can't laod in tp gt 1 (#18828) · c68b5c63
  rongfu.leng authored May 29, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  c68b5c63
- Enable Pydantic mypy checks and convert configs to Pydantic dataclasses (#17599) · 4c2b38ce
  Harry Mellor authored May 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4c2b38ce
- [Bugfix] Fix nomic max_model_len (#18755) · 3e9ce609
  wang.yuqi authored May 28, 2025
  
  3e9ce609
27 May, 2025 10 commits
- [Neuron] Support quantization on neuron (#18283) · e0cbad4e
  Satyajith Chilappagari authored May 27, 2025
```
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
```
  e0cbad4e
- [Core] Automatically cast multi-modal input dtype (#18756) · 696259ca
  Cyrus Leung authored May 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  696259ca
- [CI/Build] Remove imports of built-in `re` (#18750) · 4318c055
  Cyrus Leung authored May 27, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4318c055
- [Doc] Convert Sphinx directives ( `{class}`, `{meth}`, `{attr}`, ...) to... · a68e293c
  Hyogeun Oh (오효근) authored May 27, 2025
```
[Doc]  Convert Sphinx directives ( `{class}`, `{meth}`, `{attr}`, ...) to MkDocs format for better documentation linking (#18663)
Signed-off-by: Zerohertz <ohg3417@gmail.com>
```
  a68e293c
- [BUG FIX] minicpm (#18739) · 68811079
  Shawn Huang authored May 27, 2025
```
Signed-off-by: huangyuxiang03 <huangyx0321@gmail.com>
Co-authored-by: huangyuxiang03 <huangyx0321@gmail.com>
```
  68811079
- feat(rocm-support): support mamba2 on rocm (#18565) · a547aeb8
  almersawi authored May 27, 2025
```
Signed-off-by: Islam Almersawi <islam.almersawi@openinnovation.ai>
Co-authored-by: Islam Almersawi <islam.almersawi@openinnovation.ai>
```
  a547aeb8
- [FEAT] [ROCm] Upgrade AITER Fused MoE kernels. (#18271) · d260f799
  vllmellm authored May 27, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  d260f799
- [Model][Gemma3] Cast image pixel values already on CPU (#18732) · b50602d5
  Lukas Geiger authored May 27, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  b50602d5
- [V1][Quantization] Add CUDA graph compatible v1 GGUF support (#18646) · 1f1b1bc0
  Isotr0py authored May 27, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  1f1b1bc0
- [Model][Gemma3] Simplify image input validation (#18710) · 0eebd748
  Lukas Geiger authored May 27, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  0eebd748
26 May, 2025 4 commits
- [Bugfix] Fix Llama GGUF initialization (#18717) · a869baca
  Cyrus Leung authored May 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  a869baca
- [Doc] Move examples and further reorganize user guide (#18666) · 82e2339b
  Cyrus Leung authored May 26, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  82e2339b
- [Model] Add support for YARN in NemotronNAS models (#18427) · 6d68030f
  Naveassaf authored May 26, 2025
```
Signed-off-by: Nave Assaf <nassaf@nvidia.com>
```
  6d68030f
- [Bugfix] Fix the lm_head in gpt_bigcode in lora mode (#6357) · 561b77a0
  Maximilien de Bayser authored May 26, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
```
  561b77a0
25 May, 2025 6 commits
- [Bugfix] Fix profiling dummy data for Pixtral (#18677) · 57fd13a7
  Cyrus Leung authored May 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  57fd13a7
- [Misc] Reduce logs on startup (#18649) · 503f8487
  Cyrus Leung authored May 25, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  503f8487
- [BUGFIX] catch subclass first for try...except (#18672) · 44073a7a
  Ning Xie authored May 25, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  44073a7a
- [VLM] Initialize video input support for InternVL models (#18499) · 75f81750
  Isotr0py authored May 25, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  75f81750
- [Misc][ModelScope] Change to use runtime VLLM_USE_MODELSCOPE (#18655) · 6ab681bc
  Mengqing Cao authored May 25, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  6ab681bc
- [MISC] correct signature for LoaderFunction (#18670) · 6c6dcd86
  Ning Xie authored May 25, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  6c6dcd86
24 May, 2025 4 commits
- [BugFix] Fix import error for fused_moe (#18642) · b9018a3f
  wangxiyuan authored May 24, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  b9018a3f
- [Model] use AutoWeightsLoader for gpt2 (#18625) · 2cd4d58d
  ztang2370 authored May 24, 2025
```
Signed-off-by: zt2370 <ztang2370@gmail.com>
```
  2cd4d58d
- [Model] Add support for Qwen2.5-Omni-7B-AWQ (Qwen2_5OmniForConditionalGeneration) (#18647) · a8593205
  Yuanhao WU authored May 24, 2025
  
  a8593205
- FIX MOE issue in AutoRound format (#18586) · ec82c3e3
  Wenhua Cheng authored May 24, 2025
```
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
```
  ec82c3e3
23 May, 2025 3 commits
- [Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454) · 4fc1bf81
  Feng XiaoLong authored May 24, 2025
```
Signed-off-by: Crucifixion-Fxl <xmufxl@gmail.com>
Co-authored-by: Crucifixion-Fxl <xmufxl@gmail.com>
```
  4fc1bf81
- [ModelOpt] Introduce VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var to control... · f2036734
  Pavani Majety authored May 23, 2025
```
[ModelOpt] Introduce VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var to control blockscale tensor allocation (#18160)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  f2036734
- [CI] Enable test_initialization to run on V1 (#16736) · 0ddf88e1
  Michael Goin authored May 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  0ddf88e1