[Model][Quantization] Add Ling-3.0-flash-fp8 support (#51265)
Signed-off-by: Isotr0py <Isotr0py@outlook.com> Co-authored-by: Isotr0py <Isotr0py@outlook.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Isotr0py
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
3b4c86e489
commit
ba1cdcfcf0
@@ -292,7 +292,7 @@ class AutoAWQConfig(QuantizationConfig):
|
||||
prefix,
|
||||
self.modules_to_not_convert,
|
||||
self.packed_modules_mapping,
|
||||
skip_with_substr=True,
|
||||
match_mode="substring",
|
||||
):
|
||||
return UnquantizedLinearMethod()
|
||||
|
||||
@@ -335,7 +335,7 @@ class AutoAWQConfig(QuantizationConfig):
|
||||
if is_layer_skipped(
|
||||
prefix,
|
||||
getattr(self, "modules_to_not_convert", []),
|
||||
skip_with_substr=True,
|
||||
match_mode="substring",
|
||||
):
|
||||
return UnquantizedFusedMoEMethod(layer.moe_config)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user