[Quantization] [Refactor] Create special "GptOssMxfp4MoeMethod" (#39604)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
This commit is contained in:
Yongye Zhu
2026-04-13 12:53:58 -04:00
committed by GitHub
parent 4d042ed85f
commit 739e5945dc
18 changed files with 129 additions and 34 deletions
@@ -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."