radu/LLamaRecipes @ Remove-Tokenizer-onPrem-vllm-InferenceThroughput

镜像来自 https://github.com/facebookresearch/llama-recipes.git

Jeff Tang 6892ea1ac9 update readme and delete stale content		11 月之前
..
hf_text_generation_inference	6d449a859b New folder structure (#1)	1 年之前
vllm	6d449a859b New folder structure (#1)	1 年之前
README.md	6892ea1ac9 update readme and delete stale content	11 月之前
llama-on-prem.md	5cedef2155 Update llama-on-prem.md	1 年之前

Running Llama 3 On-Prem with vLLM and TGI

This tutorial shows how to use Llama 3 with vLLM and Hugging Face TGI to build Llama 3 on-prem apps.