[Model][Quantization] Add GGUF support for MiniMax-M2.1 (#36965)

Signed-off-by: kangletian <Letian.Kang@amd.com>
This commit is contained in:
PikaPikachu
2026-03-30 14:24:06 +08:00
committed by GitHub
parent fec5aeca12
commit 63babd17f1
5 changed files with 137 additions and 10 deletions
+1
View File
@@ -948,6 +948,7 @@ class ModelConfig:
# imports during override detection (e.g., MXFP4 imports Triton)
"mxfp4",
"cpu_awq",
"gguf",
]
quantization_methods = [
q for q in supported_quantization if q not in overrides