phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 16:29:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into henrytu/cerebras-integration

Browse source
This commit is contained in:
Henry Tu 2024-12-02 10:57:59 -05:00 • committed by GitHub
commit c29e3271d3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
38 changed files with 523 additions and 139 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -21,6 +21,7 @@ from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
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.tests.resolver import construct_stack_for_test
@ -172,6 +173,22 @@ def inference_nvidia() -> 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",
"cerebras",
"nvidia",
"tgi",
]