[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:
@@ -243,7 +243,7 @@ def test_distributed(
|
||||
"model, quantization_kwargs",
|
||||
[
|
||||
("TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ", {}),
|
||||
("TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ", {}),
|
||||
("LnL-AI/TinyLlama-1.1B-Chat-v1.0-GPTQ-4bit", {}),
|
||||
],
|
||||
)
|
||||
@pytest.mark.parametrize("max_tokens", [32])
|
||||
|
||||
Reference in New Issue
Block a user