开源雷达国内 GitHub 镜像站
加速通道已就绪 返回列表
全部项目

sanowl/Efficient-LLM-Scheduling-by-Learning-to-Rank

This project implements an efficient scheduling system for Large Language Model (LLM) inference, as described in the paper "Efficient LLM Scheduling by Learning to Rank"

语言:Python · GitHub 星标:9 · Fork:0

在 GitHub 上查看原仓库

正在读取项目信息…