[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)
Signed-off-by: Roderick-Wu <roderickwu2003@gmail.com> Signed-off-by: Roderick Wu <roderickwu2003@gmail.com> Signed-off-by: mgoin <mgoin64@gmail.com> Co-authored-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
@@ -9,8 +9,7 @@ if not current_platform.is_cpu():
|
||||
|
||||
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
|
||||
"Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4",
|
||||
"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 linear
|
||||
|
||||
Reference in New Issue
Block a user