LLM deploy vLLM SGLang FasterTransformer lmdeploy

LLM deploy for inference (tensor parallelism, data parallelism, pipeline parallelism, expert parallelism for MOE)

vLLM worker or SGLang worker or https://github.com/NVIDIA/FasterTransformer or https://github.com/InternLM/lmdeploy)

AI 正在生成文章中。。。