[Quantization] [Refactor] Create special "GptOssMxfp4MoeMethod" (#39604)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
@@ -150,7 +150,7 @@ class Base(
|
||||
if self.quant_config:
|
||||
quant_method_name = self.quant_config.get_name()
|
||||
# Check for unsupported quantization methods.
|
||||
if quant_method_name == "mxfp4":
|
||||
if quant_method_name in ("mxfp4", "gpt_oss_mxfp4"):
|
||||
raise NotImplementedError(
|
||||
"Transformers modeling backend does "
|
||||
"not support MXFP4 quantization yet."
|
||||
|
||||
Reference in New Issue
Block a user