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 16, 08:15 UTC
main
[torch.compile] Adding torch compile to vision-language models (#9946)
Yongzao committed about 2 years ago
[CI/Build] Quoting around > (#9956)
Nikita Furin committed about 2 years ago
[3/N] model runner pass the whole config to model (#9958)
youkaichao committed about 2 years ago
[bugfix] fix chatglm dummy_data_for_glmv (#9955)
youkaichao committed about 2 years ago
[V1] Fix `EngineArgs` refactor on V1 (#9954)
Robert Shaw committed about 2 years ago
[2/N] executor pass the complete config to worker/modelrunner (#9938)
youkaichao committed about 2 years ago
[Doc] Updated tpu-installation.rst with more details (#9926)
Michael Green committed about 2 years ago
[Docs] Update Granite 3.0 models in supported models table (#9930)
Nick Hill committed about 2 years ago
[torch.compile] fix cpu broken code (#9947)
youkaichao committed about 2 years ago
[Encoder Decoder] Add flash_attn kernel support for encoder-decoder models (#9559)
sroy745 committed about 2 years ago
[ci/build] Have dependabot ignore pinned dependencies (#9935)
Kevin H. Luu committed about 2 years ago
[Core][VLM] Add precise multi-modal placeholder tracking (#8346)
Peter Salas committed about 2 years ago
[ci/build] Bump the patch-update group with 10 updates (#9897)
dependabot[bot] committed about 2 years ago
[Bugfix] PicklingError on RayTaskError (#9934)
Gene Der Su committed about 2 years ago
[1/N] pass the complete config from engine to executor (#9933)
youkaichao committed about 2 years ago
[Bugfix/Core] Flashinfer k_scale and v_scale (#9861)
Pavani Majety committed about 2 years ago
[torch.compile] use interpreter with stable api from pytorch (#9889)
youkaichao committed about 2 years ago
[Core] Refactor: Clean up unused argument in Scheduler._preempt (#9696)
André Jonasson committed about 2 years ago
[Bugfix] Fix edge cases for MistralTokenizer (#9625)
Travis Johnson committed about 2 years ago
[Frontend] Use a proper chat template for VLM2Vec (#9912)
Cyrus Leung committed about 2 years ago