phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 18:53:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into change-default-embedding-model

Browse source
This commit is contained in:
Francisco Arceo 2025-10-14 10:05:04 -04:00 • committed by GitHub
commit da35f2452e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 473 additions and 231 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tests/integration/inference/test_openai_completion.py
View file

@ -58,7 +58,6 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
# does not work with the specified model, gpt-5-mini. Please choose different model and try
# again. You can learn more about which models can be used with each operation here:
# https://go.microsoft.com/fwlink/?linkid=2197993.'}}"}
"remote::watsonx", # return 404 when hitting the /openai/v1 endpoint
"remote::llama-openai-compat",
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI completions.")
@ -68,6 +67,7 @@ def skip_if_doesnt_support_completions_logprobs(client_with_models, model_id):
provider_type = provider_from_model(client_with_models, model_id).provider_type
if provider_type in (
"remote::ollama", # logprobs is ignored
"remote::watsonx",
):
pytest.skip(f"Model {model_id} hosted by {provider_type} doesn't support /v1/completions logprobs.")
@ -110,6 +110,7 @@ def skip_if_doesnt_support_n(client_with_models, model_id):
# 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
"remote::watsonx",
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support n param.")
@ -124,7 +125,6 @@ def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, mode
"remote::databricks",
"remote::cerebras",
"remote::runpod",
"remote::watsonx", # watsonx returns 404 when hitting the /openai/v1 endpoint
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI chat completions.")
@ -508,6 +508,12 @@ def test_openai_chat_completion_non_streaming_with_file(openai_client, client_wi
assert "hello world" in normalized_content
def skip_if_doesnt_support_completions_stop_sequence(client_with_models, model_id):
provider_type = provider_from_model(client_with_models, model_id).provider_type
if provider_type in ("remote::watsonx",): # openai.BadRequestError: Error code: 400
pytest.skip(f"Model {model_id} hosted by {provider_type} doesn't support /v1/completions stop sequence.")
@pytest.mark.parametrize(
"test_case",
[
@ -516,6 +522,7 @@ def test_openai_chat_completion_non_streaming_with_file(openai_client, client_wi
)
def test_openai_completion_stop_sequence(client_with_models, openai_client, text_model_id, test_case):
skip_if_model_doesnt_support_openai_completion(client_with_models, text_model_id)
skip_if_doesnt_support_completions_stop_sequence(client_with_models, text_model_id)
tc = TestCase(test_case)

14
tests/integration/inference/test_openai_embeddings.py
View file

@ -50,11 +50,15 @@ def skip_if_model_doesnt_support_encoding_format_base64(client, model_id):
def skip_if_model_doesnt_support_variable_dimensions(client_with_models, model_id):
provider = provider_from_model(client_with_models, model_id)
if provider.provider_type in (
"remote::together", # returns 400
"inline::sentence-transformers",
# Error code: 400 - {'error_code': 'BAD_REQUEST', 'message': 'Bad request: json: unknown field "dimensions"\n'}
"remote::databricks",
if (
provider.provider_type
in (
"remote::together", # returns 400
"inline::sentence-transformers",
# Error code: 400 - {'error_code': 'BAD_REQUEST', 'message': 'Bad request: json: unknown field "dimensions"\n'}
"remote::databricks",
"remote::watsonx", # openai.BadRequestError: Error code: 400 - {'detail': "litellm.UnsupportedParamsError: watsonx does not support parameters: {'dimensions': 384}
)
):
pytest.skip(
f"Model {model_id} hosted by {provider.provider_type} does not support variable output embedding dimensions."