a1c67e6db8d59c05b8785c48c1c189e6e708a2a0
Description
A high-throughput and memory-efficient inference and serving engine for LLMs
324 MiB
Languages
Python
83%
Rust
6.1%
Cuda
4.1%
C++
2.9%
JavaScript
1.9%
Other
1.9%