The Local LLM Index / Quantization & Formats / #217
bytedance/ABQ-LLM
by bytedance · Quantization & Formats · updated 1y ago
An acceleration library that supports arbitrary bit-width combinatorial quantization operations
27
momentum
245
stars
21
forks
#217
rank
cudallm-inferencemlsysquantized-networksresearch
View on GitHub →