A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 23:30 UTC
main
[Frontend] Generate valid tool call IDs when using `tokenizer-mode=mistral` (#12332)
Rafael Vasquez committed almost 2 years ago
[Bugfix] Fix num video tokens calculation for Qwen2-VL (#13148)
Cyrus Leung committed almost 2 years ago
[Bug] [V1] Try fetching stop_reason from EngineOutput before checking the request (#13108)
bnellnm committed almost 2 years ago
[Misc] AMD Build Improvements (#12923)
Shiyan Deng committed almost 2 years ago
Further reduce the HTTP calls to huggingface.co (#13107)
Maximilien de Bayser committed almost 2 years ago
Bump actions/setup-python from 5.3.0 to 5.4.0 (#12672)
dependabot[bot] committed almost 2 years ago
Bump helm/chart-testing-action from 2.6.1 to 2.7.0 (#12463)
dependabot[bot] committed almost 2 years ago
Bump actions/stale from 9.0.0 to 9.1.0 (#12462)
dependabot[bot] committed almost 2 years ago
Bump helm/kind-action from 1.10.0 to 1.12.0 (#11612)
dependabot[bot] committed almost 2 years ago
Lingfan Yu committed almost 2 years ago
[ci] Add more source file dependencies for some tests (#13123)
Kevin H. Luu committed almost 2 years ago
[Model] IBM/NASA Prithvi Geospatial model (#12830)
Christian Pinto committed almost 2 years ago
[RFC][vllm-API] Support tokenizer registry for customized tokenizer in vLLM (#12518)
Keyun Tong committed almost 2 years ago
[Misc] Move pre-commit suggestion back to the end (#13114)
Russell Bryant committed almost 2 years ago
[Bugfix] Guided decoding falls back to outlines when fails to import xgrammar (#12976)
Yuan Tang committed almost 2 years ago
[Doc] Improve OpenVINO installation doc (#13102)
Harry Mellor committed almost 2 years ago
[CI/Build][Bugfix] Fix CPU backend default threads num (#13077)
Li, Jiang committed almost 2 years ago
Fix initializing GGUF weights for ColumnParallelLinear when using tensor parallel > 1 (#13023)
Szymon Ożóg committed almost 2 years ago
[BugFix] Pop instead of del CUDA_VISIBLE_DEVICES (#12962)
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed almost 2 years ago
[Bugfix] Do not use resource module on Windows (#12858) (#13029)
MoonRide303 committed almost 2 years ago