[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:
@@ -34,10 +34,7 @@ def test_weight_loading(vllm_runner):
|
||||
"""
|
||||
|
||||
# MoE models need fp16.
|
||||
NEEDS_FP16 = (
|
||||
QUANTIZATION == "gptq"
|
||||
or MODEL_NAME == "nm-testing/test-w4a16-mixtral-actorder-group"
|
||||
)
|
||||
NEEDS_FP16 = QUANTIZATION == "gptq"
|
||||
with vllm_runner(
|
||||
model_name=MODEL_NAME,
|
||||
revision=REVISION,
|
||||
|
||||
Reference in New Issue
Block a user