mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
5cdb29758a
This adds initial streaming support to the Responses API. This PR makes sure that the _first_ inference call made to chat completions streams out. There's more to be done: - tool call output tokens need to stream out when possible - we need to loop through multiple rounds of inference and they all need to stream out. ## Test Plan Added a test. Executed as: ``` FIREWORKS_API_KEY=... \ pytest -s -v 'tests/verifications/openai_api/test_responses.py' \ --provider=stack:fireworks --model meta-llama/Llama-4-Scout-17B-16E-Instruct ``` Then, started a llama stack fireworks distro and tested against it like this: ``` OPENAI_API_KEY=blah \ pytest -s -v 'tests/verifications/openai_api/test_responses.py' \ --base-url http://localhost:8321/v1/openai/v1 \ --model meta-llama/Llama-4-Scout-17B-16E-Instruct ```
40 lines
1.7 KiB
Python
40 lines
1.7 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from tests.verifications.openai_api.fixtures.fixtures import _load_all_verification_configs
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
"""Dynamically parametrize tests based on the selected provider and config."""
|
|
if "model" in metafunc.fixturenames:
|
|
model = metafunc.config.getoption("model")
|
|
if model:
|
|
metafunc.parametrize("model", [model])
|
|
return
|
|
|
|
provider = metafunc.config.getoption("provider")
|
|
if not provider:
|
|
print("Warning: --provider not specified. Skipping model parametrization.")
|
|
metafunc.parametrize("model", [])
|
|
return
|
|
|
|
try:
|
|
config_data = _load_all_verification_configs()
|
|
except (OSError, FileNotFoundError) as e:
|
|
print(f"ERROR loading verification configs: {e}")
|
|
config_data = {"providers": {}}
|
|
|
|
provider_config = config_data.get("providers", {}).get(provider)
|
|
if provider_config:
|
|
models = provider_config.get("models", [])
|
|
if models:
|
|
metafunc.parametrize("model", models)
|
|
else:
|
|
print(f"Warning: No models found for provider '{provider}' in config.")
|
|
metafunc.parametrize("model", []) # Parametrize empty if no models found
|
|
else:
|
|
print(f"Warning: Provider '{provider}' not found in config. No models parametrized.")
|
|
metafunc.parametrize("model", []) # Parametrize empty if provider not found
|