Skip to content

Support GPTQ/Marlin format quantization (4bit weight, f16 input) #284

Support GPTQ/Marlin format quantization (4bit weight, f16 input)

Support GPTQ/Marlin format quantization (4bit weight, f16 input) #284

Annotations

7 warnings

Check (ubuntu-latest, stable)

succeeded Oct 14, 2024 in 16s