phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into use-openai-for-cerebras

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-23 16:21:31 -04:00
commit e3ad762383
29 changed files with 11729 additions and 172 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/integration/inference/test_openai_completion.py
View file

@ -99,6 +99,7 @@ def skip_if_doesnt_support_n(client_with_models, model_id):
"remote::together", # `n` > 1 is not supported when streaming tokens. Please disable `stream`
# Error code 400 - {'message': '"n" > 1 is not currently supported', 'type': 'invalid_request_error', 'param': 'n', 'code': 'wrong_api_format'}
"remote::cerebras",
"remote::databricks", # Bad request: parameter "n" must be equal to 1 for streaming mode
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support n param.")
@ -111,6 +112,7 @@ def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, mode
"inline::vllm",
"remote::bedrock",
"remote::databricks",
"remote::cerebras",
"remote::runpod",
"remote::watsonx", # watsonx returns 404 when hitting the /openai/v1 endpoint
):