[CI/Build] Fix tensorizer test for load_format change (#22583)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
This commit is contained in:
@ -426,7 +426,6 @@ steps:
|
||||
|
||||
- label: Tensorizer Test # 11min
|
||||
mirror_hardwares: [amdexperimental]
|
||||
soft_fail: true
|
||||
source_file_dependencies:
|
||||
- vllm/model_executor/model_loader
|
||||
- tests/tensorizer_loader
|
||||
|
@ -44,7 +44,7 @@ def model_uri(tmp_dir):
|
||||
def tensorize_model_and_lora(tmp_dir, model_uri):
|
||||
tensorizer_config = TensorizerConfig(tensorizer_uri=model_uri,
|
||||
lora_dir=tmp_dir)
|
||||
args = EngineArgs(model=MODEL_NAME, device="cuda")
|
||||
args = EngineArgs(model=MODEL_NAME)
|
||||
|
||||
tensorize_lora_adapter(LORA_PATH, tensorizer_config)
|
||||
tensorize_vllm_model(args, tensorizer_config)
|
||||
|
@ -166,7 +166,7 @@ def test_load_without_tensorizer_load_format(vllm_runner, capfd, model_ref):
|
||||
combined_output = out + err
|
||||
assert ("ValueError: Model loader extra config "
|
||||
"is not supported for load "
|
||||
"format LoadFormat.AUTO") in combined_output
|
||||
"format auto") in combined_output
|
||||
finally:
|
||||
del model
|
||||
gc.collect()
|
||||
@ -186,7 +186,7 @@ def test_raise_value_error_on_invalid_load_format(vllm_runner, capfd,
|
||||
|
||||
combined_output = out + err
|
||||
assert ("ValueError: Model loader extra config is not supported "
|
||||
"for load format LoadFormat.SAFETENSORS") in combined_output
|
||||
"for load format safetensors") in combined_output
|
||||
finally:
|
||||
del model
|
||||
gc.collect()
|
||||
|
Reference in New Issue
Block a user