[CPU] Add MXFP4 W4A16 MoE support (#41922)
Signed-off-by: yuwenzho <yuwen.zhou@intel.com> Signed-off-by: Yuwen Zhou <yuwen.zhou@intel.com>
This commit is contained in:
@@ -15,6 +15,7 @@ MODELS = [
|
||||
"OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc",
|
||||
"Qwen/Qwen3-0.6B-FP8", # FP8 W8A16 block-quantized linear
|
||||
"Qwen/Qwen3-30B-A3B-FP8", # FP8 W8A16 block-quantized MoE
|
||||
"openai/gpt-oss-20b", # MXFP4 W4A16
|
||||
]
|
||||
DTYPE = ["bfloat16"]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user