Set use_fast=True by default, create --no_use_fast flag
This increases tokens/second for HF loaders.
This commit is contained in:
parent
b2ce8dc7ee
commit
8b66d83aa9
6 changed files with 20 additions and 19 deletions
|
@ -52,7 +52,7 @@ def list_model_elements():
|
|||
'bf16',
|
||||
'load_in_8bit',
|
||||
'trust_remote_code',
|
||||
'use_fast',
|
||||
'no_use_fast',
|
||||
'use_flash_attention_2',
|
||||
'load_in_4bit',
|
||||
'compute_dtype',
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue