comtam
PublicA simple backend for LLM inference written in C++17, Metal (for GPU) and AVX/NEON (for CPU).
Creat:2025-05-04T00:36:25
Update:2025-06-10T10:44:13
1
Stars
0
Stars Increase
A simple backend for LLM inference written in C++17, Metal (for GPU) and AVX/NEON (for CPU).