Skip to content

Commit

Permalink
linting change
Browse files Browse the repository at this point in the history
  • Loading branch information
saileshd1402 committed Jan 4, 2024
1 parent a36e022 commit bcef8ed
Showing 1 changed file with 4 additions and 2 deletions.
6 changes: 4 additions & 2 deletions llm/kubeflow_inference_run.py
Original file line number Diff line number Diff line change
Expand Up @@ -388,8 +388,10 @@ def execute(params: argparse.Namespace) -> None:
model_info["repo_version"] = check_if_valid_version(model_info, mount_path)

if quantize_bits and int(quantize_bits) not in [4, 8]:
print("## Quantization precision bits should be either 4 or 8."
" Default precision used is 16 (bfloat16)")
print(
"## Quantization precision bits should be either 4 or 8."
" Default precision used is 16 (bfloat16)"
)
sys.exit(1)
elif quantize_bits and deployment_resources["gpus"]:
print("## BitsAndBytes Quantization requires GPUs")
Expand Down

0 comments on commit bcef8ed

Please sign in to comment.