AutoGPTQ TVM
Free40 GitHub stars
Agent ToolAgnosticFile System
Overview
AutoGPTQ TVM provides a kernel for efficient inference of GPTQ models using TVM. It is designed for developers looking to optimize their AI model performance on local systems.
AutoGPTQ TVM provides a kernel for efficient inference of GPTQ models using TVM. It is designed for developers looking to optimize their AI model performance on local systems.