[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:
@@ -30,7 +30,7 @@ def models_list(*, all: bool = True, keywords: list[str] | None = None):
|
||||
if is_quant_method_supported("gptq_marlin"):
|
||||
TEST_MODELS.append(
|
||||
(
|
||||
"TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ",
|
||||
"LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit",
|
||||
{"quantization": "gptq_marlin"},
|
||||
)
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user