Enable ModelOpt FP8 emulation on SM80 (#50019)
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Michael Goin
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
454ea5b526
commit
e3be89673d
@@ -405,7 +405,7 @@ class ModelOptFp8Config(ModelOptQuantConfigBase):
|
||||
|
||||
@classmethod
|
||||
def get_min_capability(cls) -> int:
|
||||
return 89
|
||||
return 80
|
||||
|
||||
@classmethod
|
||||
def override_quantization_method(
|
||||
|
||||
Reference in New Issue
Block a user