[CPU] Support CT W4A16 on CPU MP kernel (#38219)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
2026-03-27 14:15:28 +08:00
parent a8eab8f30d
commit becaed6ec8
2 changed files with 42 additions and 20 deletions
--- a/tests/quantization/test_cpu_wna16.py
+++ b/tests/quantization/test_cpu_wna16.py
@@ -11,6 +11,7 @@ MODELS = [
    "TheBloke/TinyLlama-1.1B-Chat-v1.0-AWQ",
    "TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ",  # with g_idx
    "Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4",  # without g_idx
+    "RedHatAI/Qwen3-1.7B-quantized.w4a16",  # with zp
 ]
 DTYPE = ["bfloat16"]