AutoGPTQ: Add --disable_exllamav2 flag (Mixtral CPU offloading needs this)

This commit is contained in:
oobabooga 2023-12-15 06:46:13 -08:00
parent 7de10f4c8e
commit 3bbf6c601d
7 changed files with 16 additions and 4 deletions

View file

@ -70,6 +70,7 @@ def list_model_elements():
'no_inject_fused_mlp',
'no_use_cuda_fp16',
'disable_exllama',
'disable_exllamav2',
'cfg_cache',
'no_flash_attn',
'cache_8bit',