[CPU] Add FP8 W8A16 linear support (#41186)

Signed-off-by: yuwenzho <yuwen.zhou@intel.com>
This commit is contained in:
Yuwen Zhou
2026-05-06 07:05:27 +00:00
committed by GitHub
parent b53c507bc9
commit 809b98e5b7
9 changed files with 331 additions and 3 deletions
+1
View File
@@ -13,6 +13,7 @@ MODELS = [
"Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4", # without g_idx
"RedHatAI/Qwen3-1.7B-quantized.w4a16", # with zp
"OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc",
"Qwen/Qwen3-0.6B-FP8", # FP8 W8A16 block-quantized
]
DTYPE = ["bfloat16"]