mirror of
https://github.com/vllm-project/vllm.git
synced 2025-10-20 14:53:52 +08:00
Use float32 for test_completion.py (#22385)
Signed-off-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
@ -20,9 +20,8 @@ MODEL_NAME = "facebook/opt-125m"
|
||||
@pytest.fixture(scope="module")
|
||||
def default_server_args():
|
||||
return [
|
||||
# use half precision for speed and memory savings in CI environment
|
||||
"--dtype",
|
||||
"bfloat16",
|
||||
"float32",
|
||||
"--max-model-len",
|
||||
"2048",
|
||||
"--max-num-seqs",
|
||||
|
Reference in New Issue
Block a user