phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-10 21:34:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-localize-url-feature-to-openaimixin

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-26 16:31:59 -04:00
commit 17125fd2cf
421 changed files with 70880 additions and 5915 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tests/integration/inference/test_openai_completion.py
View file

@ -40,7 +40,6 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
"inline::sentence-transformers",
"inline::vllm",
"remote::bedrock",
"remote::cerebras",
"remote::databricks",
# Technically Nvidia does support OpenAI completions, but none of their hosted models
# support both completions and chat completions endpoint and all the Llama models are
@ -98,6 +97,9 @@ def skip_if_doesnt_support_n(client_with_models, model_id):
# the entered value was 2. Update the candidateCount value and try again.', 'status': 'INVALID_ARGUMENT'}
"remote::tgi", # TGI ignores n param silently
"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.")
@ -109,8 +111,8 @@ def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, mode
"inline::sentence-transformers",
"inline::vllm",
"remote::bedrock",
"remote::cerebras",
"remote::databricks",
"remote::cerebras",
"remote::runpod",
"remote::watsonx", # watsonx returns 404 when hitting the /openai/v1 endpoint
):

9
tests/integration/inference/test_openai_embeddings.py
View file

@ -33,6 +33,7 @@ def skip_if_model_doesnt_support_user_param(client, model_id):
provider = provider_from_model(client, model_id)
if provider.provider_type in (
"remote::together", # service returns 400
"remote::fireworks", # service returns 400 malformed input
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support user param.")
@ -40,7 +41,9 @@ def skip_if_model_doesnt_support_user_param(client, model_id):
def skip_if_model_doesnt_support_encoding_format_base64(client, model_id):
provider = provider_from_model(client, model_id)
if provider.provider_type in (
"remote::together", # param silently ignored, always returns floats
"remote::databricks", # param silently ignored, always returns floats
"remote::fireworks", # param silently ignored, always returns list of floats
"remote::ollama", # param silently ignored, always returns list of floats
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support encoding_format='base64'.")
@ -50,6 +53,8 @@ def skip_if_model_doesnt_support_variable_dimensions(client_with_models, model_i
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",
):
pytest.skip(
f"Model {model_id} hosted by {provider.provider_type} does not support variable output embedding dimensions."
@ -73,7 +78,6 @@ def skip_if_model_doesnt_support_openai_embeddings(client, model_id):
"inline::meta-reference",
"remote::bedrock",
"remote::cerebras",
"remote::databricks",
"remote::runpod",
"remote::sambanova",
"remote::tgi",
@ -287,7 +291,6 @@ def test_openai_embeddings_base64_batch_processing(compat_client, client_with_mo
input=input_texts,
encoding_format="base64",
)
# Validate response structure
assert response.object == "list"
assert response.model == embedding_model_id