[CPU] Support CPU W4A16 INT4 MoE (#43409)

Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
This commit is contained in:
Yuwen Zhou
2026-06-12 07:12:37 +00:00
committed by GitHub
parent a2c72d4388
commit 0cd9b7af25
8 changed files with 685 additions and 22 deletions
+3
View File
@@ -16,6 +16,9 @@ MODELS = [
"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
"QuixiAI/Qwen3-30B-A3B-AWQ", # AWQ W4A16 MoE
"Qwen/Qwen3-30B-A3B-GPTQ-Int4", # GPTQ W4A16 MoE
"RedHatAI/Qwen3-30B-A3B-quantized.w4a16", # compressed-tensors W4A16 MoE
]
DTYPE = ["bfloat16"]