The Local LLM Index / Quantization & Formats / #68
ModelCloud/GPTQModel
by ModelCloud · Quantization & Formats · updated today
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
67
momentum
1,253
stars
206
forks
#68
rank
gptqoptimumpeftquantizationsglangtransformersvllm
View on GitHub →