phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 18:32:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add Groq provider - chat completions

Browse source
This commit is contained in:
Aidan Do 2024-12-12 21:15:09 +11:00
parent c294a01c4b
commit 378150e23c
10 changed files with 727 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -19,6 +19,7 @@ from llama_stack.providers.remote.inference.bedrock import BedrockConfig
from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
from llama_stack.providers.remote.inference.groq import GroqConfig
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
@ -150,6 +151,22 @@ def inference_together() -> ProviderFixture:
)
@pytest.fixture(scope="session")
def inference_groq() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="groq",
provider_type="remote::groq",
config=GroqConfig().model_dump(),
)
],
provider_data=dict(
groq_api_key=get_env_or_fail("GROQ_API_KEY"),
),
)
@pytest.fixture(scope="session")
def inference_bedrock() -> ProviderFixture:
return ProviderFixture(
@ -222,6 +239,7 @@ INFERENCE_FIXTURES = [
"ollama",
"fireworks",
"together",
"groq",
"vllm_remote",
"remote",
"bedrock",