Add the --disable_exllama option for AutoGPTQ

This commit is contained in:
Chris Lefever 2023-08-12 02:26:58 -04:00
parent 0e05818266
commit 0230fa4e9c
6 changed files with 6 additions and 0 deletions

View file

@ -50,6 +50,7 @@ def load_quantized(model_name):
'max_memory': get_max_memory_dict(),
'quantize_config': quantize_config,
'use_cuda_fp16': not shared.args.no_use_cuda_fp16,
'disable_exllama': shared.args.disable_exllama,
}
logger.info(f"The AutoGPTQ params are: {params}")