Skip to content

fix: use min_output_len value in query_llm inputs #721

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
andrewwhitecdw wants to merge 1 commit into
base: main
Choose a base branch
from
+5 −2
Open

fix: use min_output_len value in query_llm inputs #721

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion nemo_deploy/llm/query_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -362,7 +362,7 @@ def query_llm(
inputs = {"prompts": prompts}

if min_output_len is not None:
inputs["min_output_len"] = np.full(prompts.shape, max_output_len, dtype=np.int_)
inputs["min_output_len"] = np.full(prompts.shape, min_output_len, dtype=np.int_)

if max_output_len is not None:
inputs["max_output_len"] = np.full(prompts.shape, max_output_len, dtype=np.int_)
Expand Down
5 changes: 4 additions & 1 deletion tests/unit_tests/deploy/test_query_llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -501,11 +501,14 @@ def test_query_llm_with_min_output_len(self, mock_client, query):
mock_instance.infer_batch.return_value = {"outputs": np.array([b"test response"])}
mock_instance.model_config.outputs = [MagicMock(dtype=np.bytes_)]

# Test query with min_output_len
# Test query with min_output_len distinct from max_output_len
response = query.query_llm(prompts=["test prompt"], min_output_len=10, max_output_len=100)

assert isinstance(response[0], str)
assert response[0] == "test response"
call_kwargs = mock_instance.infer_batch.call_args.kwargs
assert call_kwargs["min_output_len"][0] == 10
assert call_kwargs["max_output_len"][0] == 100

@patch("nemo_deploy.llm.query_llm.ModelClient")
def test_query_llm_with_logits_output(self, mock_client, query):
Expand Down
Loading