phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 19:04:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Allow overriding MODEL_IDS for inference test

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-17 10:03:27 -07:00
parent 02be26098a
commit 9fcf5d58e0
1 changed files with 8 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/tests/inference/test_inference.py
View file

@ -5,6 +5,7 @@
# the root directory of this source tree. # the root directory of this source tree.
import itertools import itertools
import os
import pytest import pytest
import pytest_asyncio import pytest_asyncio
@ -50,14 +51,17 @@ def get_expected_stop_reason(model: str):
return StopReason.end_of_message if "Llama3.1" in model else StopReason.end_of_turn return StopReason.end_of_message if "Llama3.1" in model else StopReason.end_of_turn
if "MODEL_IDS" not in os.environ:
MODEL_IDS = [Llama_8B, Llama_3B]
else:
MODEL_IDS = os.environ["MODEL_IDS"].split(",")
# This is going to create multiple Stack impls without tearing down the previous one # This is going to create multiple Stack impls without tearing down the previous one
# Fix that! # Fix that!
@pytest_asyncio.fixture( @pytest_asyncio.fixture(
scope="session", scope="session",
params=[ params=[{"model": m} for m in MODEL_IDS],
{"model": Llama_8B},
{"model": Llama_3B},
],
ids=lambda d: d["model"], ids=lambda d: d["model"],
) )
async def inference_settings(request): async def inference_settings(request):