[Quantization][Autoround][CPU] Add W4A16 Support (#38192)
Signed-off-by: Zhenzhong1 <zhenzhong.xu@intel.com> Signed-off-by: Zhenzhong Xu <zhenzhong.xu@intel.com>
This commit is contained in:
@@ -12,6 +12,7 @@ MODELS = [
|
||||
"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
|
||||
"OPEA/Qwen2.5-0.5B-Instruct-int4-sym-inc",
|
||||
]
|
||||
DTYPE = ["bfloat16"]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user