Skip to content

Add support for GPTQ-quantized MoE models using MoE Marlin #1226

Add support for GPTQ-quantized MoE models using MoE Marlin

Add support for GPTQ-quantized MoE models using MoE Marlin #1226

Annotations

1 error and 1 warning

build (cuda)  /  integration_tests

failed Sep 24, 2024 in 46m 46s