phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into fix/nvidia-safety-provider-endpoint-4189

Browse source
This commit is contained in:
Roy Belio 2025-11-20 13:30:11 +02:00 • committed by GitHub
commit f8f28344a5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
117 changed files with 16294 additions and 769 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/unit/providers/nvidia/test_rerank_inference.py
View file

@ -146,7 +146,7 @@ async def test_hosted_model_not_in_endpoint_mapping():
async def test_self_hosted_ignores_endpoint():
adapter = create_adapter(
config=NVIDIAConfig(url="http://localhost:8000", api_key=None),
config=NVIDIAConfig(base_url="http://localhost:8000", api_key=None),
rerank_endpoints={"test-model": "https://model.endpoint/rerank"}, # This should be ignored for self-hosted.
)
mock_session = MockSession(MockResponse())