mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
787e2034b7
tests: pytest -v -s -m "ollama" llama_stack/providers/tests/inference/test_text_inference.py pytest -v -s -m vllm_remote llama_stack/providers/tests/inference/test_text_inference.py --env VLLM_URL="http://localhost:9798/v1" ---------
35 lines
1.1 KiB
Python
35 lines
1.1 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import pytest
|
|
|
|
# How to run this test:
|
|
#
|
|
# pytest -v -s llama_stack/providers/tests/inference/test_model_registration.py
|
|
# -m "meta_reference"
|
|
# --env TOGETHER_API_KEY=<your_api_key>
|
|
|
|
|
|
class TestModelRegistration:
|
|
@pytest.mark.asyncio
|
|
async def test_register_unsupported_model(self, inference_stack):
|
|
_, models_impl = inference_stack
|
|
|
|
# Try to register a model that's too large for local inference
|
|
with pytest.raises(Exception) as exc_info:
|
|
await models_impl.register_model(
|
|
model_id="Llama3.1-70B-Instruct",
|
|
)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_register_nonexistent_model(self, inference_stack):
|
|
_, models_impl = inference_stack
|
|
|
|
# Try to register a non-existent model
|
|
with pytest.raises(Exception) as exc_info:
|
|
await models_impl.register_model(
|
|
model_id="Llama3-NonExistent-Model",
|
|
)
|