Commits · d0a7a2769d92619afdcdc3b91c78098eaa9e38c0 · OpenDAS / vllm_cscc · GitLab

19 Feb, 2025 2 commits
- [Hardware][Gaudi][Feature] Support Contiguous Cache Fetch (#12139) · d0a7a276
  Yu-Zhou authored Feb 19, 2025
```
Signed-off-by: yuzhou <yuzhou@habana.ai>
Signed-off-by: zhouyu5 <yu.zhou@intel.com>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
```
  d0a7a276
- [Misc] Remove dangling references to `--use-v2-block-manager` (#13492) · 00b69c2d
  Harry Mellor authored Feb 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  00b69c2d
18 Feb, 2025 26 commits
- [V1][Spec Decode] Optimize N-gram matching with Numba (#13365) · 4c822298
  Woosuk Kwon authored Feb 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  4c822298
- Pin Ray version to 2.40.0 (#13490) · c8d70e24
  Woosuk Kwon authored Feb 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  c8d70e24
- [V1] Optimize handling of sampling metadata and req_ids list (#13244) · 30172b49
  Nick Hill authored Feb 18, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  30172b49
- [V1][Tests] Adding additional testing for multimodal models to V1 (#13308) · a4d577b3
  Murali Andoorveedu authored Feb 18, 2025
```
Signed-off-by: andoorve <37849411+andoorve@users.noreply.github.com>
```
  a4d577b3
- [misc] fix debugging code (#13487) · 7b203b76
  youkaichao authored Feb 19, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  7b203b76
- [V1][PP] Enable true PP with Ray executor (#13472) · 4fb8142a
  Woosuk Kwon authored Feb 18, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  4fb8142a
- [CI/Build] migrate static project metadata from setup.py to pyproject.toml (#8772) · a02c86b4
  Daniele authored Feb 18, 2025
  
  a02c86b4
- [Bugfix] Fix invalid rotary embedding unit test (#13431) · 38094584
  Liangfu Chen authored Feb 18, 2025
```
Signed-off-by: Liangfu Chen <liangfc@amazon.com>
```
  38094584
- [Bugfix] Handle content type with optional parameters (#13383) · d3231cb4
  zifeitong authored Feb 18, 2025
```
Signed-off-by: Zifei Tong <zifeitong@gmail.com>
```
  d3231cb4
- [ROCm] Make amdsmi import optional for other platforms (#13460) · 435b502a
  Cyrus Leung authored Feb 18, 2025
  
  435b502a
- [Bugfix] Remove noisy error logging during local model loading (#13458) · 29fc5772
  Isotr0py authored Feb 18, 2025
  
  29fc5772
- [Doc]: Improve feature tables (#13224) · 2358ca52
  Harry Mellor authored Feb 18, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2358ca52
- [Bugfix] Fix failing transformers dynamic module resolving with spawn multiproc method (#13403) · 8cf97f86
  Isotr0py authored Feb 18, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  8cf97f86
- [Bugfix] Ensure LoRA path from the request can be included in err msg (#13450) · e2603fef
  Yuan Tang authored Feb 18, 2025
```
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
```
  e2603fef
- Add outlines fallback when JSON schema has enum (#13449) · b53d7998
  Michael Goin authored Feb 18, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  b53d7998
- [V1][PP] Fix & Pin Ray version in requirements-cuda.txt (#13436) · 9915912f
  Woosuk Kwon authored Feb 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  9915912f
- [Quant] Aria SupportsQuant (#13416) · d1b649f1
  Kyle Sayers authored Feb 18, 2025
  
  d1b649f1
- [core] fix sleep mode in pytorch 2.6 (#13456) · ac19b519
  youkaichao authored Feb 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  ac19b519
- [Bugfix] Only print out chat template when supplied (#13444) · a1074b3e
  Yuan Tang authored Feb 18, 2025
  
  a1074b3e
- [Quant] Arctic SupportsQuant (#13366) · 00294e1b
  Kyle Sayers authored Feb 18, 2025
  
  00294e1b
- [Quant] Molmo SupportsQuant (#13336) · 88787bce
  Kyle Sayers authored Feb 18, 2025
  
  88787bce
- [v1] fix parallel config rank (#13445) · 932b51ce
  youkaichao authored Feb 18, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  932b51ce
- [ROCm] fix get_device_name for rocm (#13438) · 7c7adf81
  Divakar Verma authored Feb 17, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  7c7adf81
- [Model] Enable quantization support for `transformers` backend (#12960) · 67ef8f66
  Isotr0py authored Feb 18, 2025
  
  67ef8f66
- [Misc] Remove dangling references to `SamplingType.BEAM` (#13402) · efbe8544
  Harry Mellor authored Feb 18, 2025
  
  efbe8544
- [Bugfix][CI][V1] Work around V1 + CUDA Graph + torch._scaled_mm fallback issue (#13425) · b3942e15
  Tyler Michael Smith authored Feb 17, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  b3942e15
17 Feb, 2025 12 commits
- [V1][Spec decode] Move drafter to model runner (#13363) · cd4a72a2
  Woosuk Kwon authored Feb 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  cd4a72a2
- [V1][PP] Fix intermediate tensor values (#13417) · 6ac485a9
  Cody Yu authored Feb 17, 2025
```
Signed-off-by: Cody Yu <hao.yu.cody@gmail.com>
```
  6ac485a9
- [V1] Get input tokens from scheduler (#13339) · 4c21ce9e
  Woosuk Kwon authored Feb 17, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  4c21ce9e
- [Bugfix] Fix VLLM_USE_MODELSCOPE issue (#13384) · ce77eb94
  r.4ntix authored Feb 17, 2025
  
  ce77eb94
- [Bugfix] fix xpu communicator (#13368) · 30513d1c
  Yan Ma authored Feb 17, 2025
```
Signed-off-by: yan ma <yan.ma@intel.com>
```
  30513d1c
- [Model] Support Mamba2 (Codestral Mamba) (#9292) · 1f69c4a8
  Tyler Michael Smith authored Feb 17, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
```
  1f69c4a8
- [VLM] Check required fields before initializing field config in `DictEmbeddingItems` (#13380) · 7b623fca
  Cyrus Leung authored Feb 17, 2025
  
  7b623fca
- [MISC] tiny fixes (#13378) · 238dfc8a
  Mengqing Cao authored Feb 17, 2025
  
  238dfc8a
- Run v1 benchmark and integrate with PyTorch OSS benchmark database (#13068) · 45186834
  Huy Do authored Feb 17, 2025
```
Signed-off-by: Huy Do <huydhn@gmail.com>
```
  45186834
- Fix spelling error in index.md (#13369) · f857311d
  yankooo authored Feb 17, 2025
  
  f857311d
- [Feature][Spec Decode] Simplify the use of Eagle Spec Decode (#12304) · 46cdd595
  shangmingc authored Feb 17, 2025
```
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
```
  46cdd595
- [V1][Misc] Avoid unnecessary log output (#13289) · 2010f04c
  Jee Jee Li authored Feb 17, 2025
  
  2010f04c