Skip to content

Allow GPTQModel to auto select Marlin or faster kernels for inference only ops #6911

Allow GPTQModel to auto select Marlin or faster kernels for inference only ops

Allow GPTQModel to auto select Marlin or faster kernels for inference only ops #6911

build (3.9, ubuntu-20.04)

succeeded Jan 7, 2025 in 1m 55s