phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-20 05:28:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into sambanova

Browse source
This commit is contained in:
Swan Htet Aung 2024-12-01 19:13:41 -06:00 • committed by GitHub
commit 7bc6cecc01
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
40 changed files with 603 additions and 145 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama_stack/providers/tests/inference/fixtures.py
View file

@ -20,6 +20,7 @@ from llama_stack.providers.remote.inference.bedrock import BedrockConfig
from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
from llama_stack.providers.remote.inference.tgi import TGIImplConfig
from llama_stack.providers.remote.inference.together import TogetherImplConfig
from llama_stack.providers.remote.inference.vllm import VLLMInferenceAdapterConfig
from llama_stack.providers.remote.inference.sambanova import SambanovaImplConfig
@ -172,6 +173,22 @@ def inference_sambanova() -> ProviderFixture:
)
@pytest.fixture(scope="session")
def inference_tgi() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="tgi",
provider_type="remote::tgi",
config=TGIImplConfig(
url=get_env_or_fail("TGI_URL"),
api_token=os.getenv("TGI_API_TOKEN", None),
).model_dump(),
)
],
)
def get_model_short_name(model_name: str) -> str:
"""Convert model name to a short test identifier.
@ -207,6 +224,7 @@ INFERENCE_FIXTURES = [
"bedrock",
"nvidia",
"sambanova",
"tgi",
]