phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

feat(providers): sambanova updated to use LiteLLM openai-compat (#1596)

Browse source 
# What does this PR do?

switch sambanova inference adaptor to LiteLLM usage to simplify
integration and solve issues with current adaptor when streaming and
tool calling, models and templates updated

## Test Plan
pytest -s -v tests/integration/inference/test_text_inference.py
--stack-config=sambanova
--text-model=sambanova/Meta-Llama-3.3-70B-Instruct

pytest -s -v tests/integration/inference/test_vision_inference.py
--stack-config=sambanova
--vision-model=sambanova/Llama-3.2-11B-Vision-Instruct
This commit is contained in:
Jorge Piedrahita Ortiz 2025-05-06 18:50:22 -05:00 • committed by GitHub
parent dd49ef31f1
commit b2b00a216b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 529 additions and 404 deletions
Download patch file Download diff file Expand all files Collapse all files

15
tests/integration/inference/test_text_inference.py
View file

@ -30,12 +30,25 @@ def skip_if_model_doesnt_support_completion(client_with_models, model_id):
"remote::anthropic",
"remote::gemini",
"remote::groq",
"remote::sambanova",
)
or "openai-compat" in provider.provider_type
):
pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support completion")
def skip_if_model_doesnt_support_json_schema_structured_output(client_with_models, model_id):
models = {m.identifier: m for m in client_with_models.models.list()}
models.update({m.provider_resource_id: m for m in client_with_models.models.list()})
provider_id = models[model_id].provider_id
providers = {p.provider_id: p for p in client_with_models.providers.list()}
provider = providers[provider_id]
if provider.provider_type in ("remote::sambanova",):
pytest.skip(
f"Model {model_id} hosted by {provider.provider_type} doesn't support json_schema structured output"
)
def get_llama_model(client_with_models, model_id):
models = {}
for m in client_with_models.models.list():
@ -384,6 +397,8 @@ def test_text_chat_completion_with_tool_choice_none(client_with_models, text_mod
],
)
def test_text_chat_completion_structured_output(client_with_models, text_model_id, test_case):
skip_if_model_doesnt_support_json_schema_structured_output(client_with_models, text_model_id)
class NBAStats(BaseModel):
year_for_draft: int
num_seasons_in_nba: int