forked from Karylab-cklius/vllm
8edcabc737c867cf237289134583c2bbc852f11e
CacheFlow
Description
A high-throughput and memory-efficient inference and serving engine for LLMs
1.6 GiB
Languages
Python
81.1%
Rust
6.5%
Cuda
4.8%
C++
3.4%
JavaScript
2.7%
Other
1.3%