V
vllm-project/vllm95.4k
A high-throughput and memory-efficient inference and serving engine for LLMs
v0.32.0Pythonamdblackwell
更新于 7 小时前Apache-2.0
02 / Repository index
按平台、分类、语言与许可组合筛选；每条记录都能回到仓库原文核对。
1 records · filtered
A high-throughput and memory-efficient inference and serving engine for LLMs