phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 16:49:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Cerebras Integration

Browse source
This commit is contained in:
Henry Tu 2024-11-20 10:20:28 -08:00
parent 34be07e0df
commit 3838bd1704
16 changed files with 515 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/providers/tests/inference/fixtures.py
View file

@ -17,6 +17,7 @@ from llama_stack.providers.inline.inference.meta_reference import (
)
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.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.ollama import OllamaImplConfig
@ -63,6 +64,21 @@ def inference_meta_reference(inference_model) -> ProviderFixture:
)
@pytest.fixture(scope="session")
def inference_cerebras() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="cerebras",
provider_type="remote::cerebras",
config=CerebrasImplConfig(
api_key=get_env_or_fail("CEREBRAS_API_KEY"),
).model_dump(),
)
],
)
@pytest.fixture(scope="session")
def inference_ollama(inference_model) -> ProviderFixture:
inference_model = (
@ -189,6 +205,7 @@ INFERENCE_FIXTURES = [
"vllm_remote",
"remote",
"bedrock",
"cerebras",
"nvidia",
]

2
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -94,6 +94,7 @@ class TestInference:
"remote::tgi",
"remote::together",
"remote::fireworks",
"remote::cerebras",
):
pytest.skip("Other inference providers don't support completion() yet")
@ -139,6 +140,7 @@ class TestInference:
"remote::tgi",
"remote::together",
"remote::fireworks",
"remote::cerebras",
):
pytest.skip(
"Other inference providers don't support structured output in completions yet"