The Local LLM Index / Quantization & Formats / #216
intel/neural-speed
by intel · Quantization & Formats · updated 2y ago
An innovative library for efficient LLM inference via low-bit quantization
29
momentum
350
stars
36
forks
#216
rank
cpufp4fp8gaudi2gpuint1int2int3int4int5int6int7
View on GitHub →