@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only
Fork 0

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, 09:30 UTC

main

[Bugfix] fix detokenizer shallow copy (#5919)

Aurick Qiao committed about 2 years ago

[Neuron] [Bugfix] Fix neuron startup (#9374)

xendo committed about 2 years ago

[V1] Implement vLLM V1 [1/N] (#9289)

Woosuk Kwon committed about 2 years ago

[Hardware][CPU] using current_platform.is_cpu (#9536)

wangshuai09 committed about 2 years ago

support TP in qwen2 bnb (#9574)

chenqianfzh committed about 2 years ago

[Doc] Use shell code-blocks and fix section headers (#9508)

Rafael Vasquez committed about 2 years ago

[Core] Remove evictor_v1 (#9572)

Kuntai Du committed about 2 years ago

← Newer Page 966 of 1120 Older →