phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 05:08:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add refresh_models support to inference adapters (default: false) (#3719)

Browse source 
# What does this PR do?

inference adapters can now configure `refresh_models: bool` to control
periodic model listing from their providers

BREAKING CHANGE: together inference adapter default changed. previously
always refreshed, now follows config.

addresses "models: refresh" on #3517

## Test Plan

ci w/ new tests
This commit is contained in:
Matthew Farrellee 2025-10-07 09:19:56 -04:00 • committed by GitHub
parent 8b9af03a1b
commit e892a3f7f4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
31 changed files with 33 additions and 67 deletions
Download patch file Download diff file Expand all files Collapse all files

40
tests/unit/providers/inference/test_remote_vllm.py
View file

@ -186,43 +186,3 @@ async def test_openai_chat_completion_is_async(vllm_inference_adapter):
assert mock_create_client.call_count == 4 # no cheating
assert total_time < (sleep_time * 2), f"Total time taken: {total_time}s exceeded expected max"
async def test_should_refresh_models():
"""
Test the should_refresh_models method with different refresh_models configurations.
This test verifies that:
1. When refresh_models is True, should_refresh_models returns True regardless of api_token
2. When refresh_models is False, should_refresh_models returns False regardless of api_token
"""
# Test case 1: refresh_models is True, api_token is None
config1 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token=None, refresh_models=True)
adapter1 = VLLMInferenceAdapter(config=config1)
result1 = await adapter1.should_refresh_models()
assert result1 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 2: refresh_models is True, api_token is empty string
config2 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="", refresh_models=True)
adapter2 = VLLMInferenceAdapter(config=config2)
result2 = await adapter2.should_refresh_models()
assert result2 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 3: refresh_models is True, api_token is "fake" (default)
config3 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="fake", refresh_models=True)
adapter3 = VLLMInferenceAdapter(config=config3)
result3 = await adapter3.should_refresh_models()
assert result3 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 4: refresh_models is True, api_token is real token
config4 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="real-token-123", refresh_models=True)
adapter4 = VLLMInferenceAdapter(config=config4)
result4 = await adapter4.should_refresh_models()
assert result4 is True, "should_refresh_models should return True when refresh_models is True"
# Test case 5: refresh_models is False, api_token is real token
config5 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="real-token-456", refresh_models=False)
adapter5 = VLLMInferenceAdapter(config=config5)
result5 = await adapter5.should_refresh_models()
assert result5 is False, "should_refresh_models should return False when refresh_models is False"