nf4-triton-kernel
An optimized, high-performance NF4 (NormalFloat 4-bit) dequantization Triton GPU kernel achieving up to 1.41x speedup over bitsandbytes.
About
An optimized, high-performance NF4 (NormalFloat 4-bit) dequantization Triton GPU kernel achieving up to 1.41x speedup over bitsandbytes.
Languages
Contributors2
No features listed.
Comments Theme
Platforms
Hosting
Self-hosted
Install
Docker
pip
