mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
c97e05f75e
# What does this PR do? This PR splits the inference tests into text and vision to make testing on vLLM provider easier as mentioned in https://github.com/meta-llama/llama-stack/pull/951 since serving multiple models (e.g. Llama-3.2-11B-Vision-Instruct and Llama-3.1-8B-Instruct) on a single port using the OpenAI API is [not supported yet](https://docs.vllm.ai/en/v0.5.5/serving/faq.html) so it's a bit tricky to test both at the same time. ## Test Plan All previously passing tests related to text still pass: `LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/inference/test_text_inference.py` All vision tests passed via `LLAMA_STACK_BASE_URL=http://localhost:5002 pytest -v tests/client-sdk/inference/test_vision_inference.py`. Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> |
||
|---|---|---|
| .. | ||
| agents | ||
| inference | ||
| safety | ||
| tool_runtime | ||
| vector_io | ||
| __init__.py | ||
| conftest.py | ||
| metadata.py | ||
| README.md | ||
| report.py | ||
Llama Stack Integration Tests
You can run llama stack integration tests on either a Llama Stack Library or a Llama Stack endpoint.
To test on a Llama Stack library with certain configuration, run
LLAMA_STACK_CONFIG=./llama_stack/templates/cerebras/run.yaml
pytest -s -v tests/client-sdk/inference/
or just the template name
LLAMA_STACK_CONFIG=together
pytest -s -v tests/client-sdk/inference/
To test on a Llama Stack endpoint, run
LLAMA_STACK_BASE_URL=http//localhost:8089
pytest -s -v tests/client-sdk/inference
Report Generation
To generate a report, run with --report option
LLAMA_STACK_CONFIG=together pytest -s -v report.md tests/client-sdk/ --report
Common options
Depending on the API, there are custom options enabled
- For tests in
inference/andagents/, we support--inference-model(to be used in text inference tests) and--vision-inference-model` (only used in image inference tests) overrides - For tests in
vector_io/, we support--embedding-modeloverride - For tests in
safety/, we support--safety-shieldoverride - The param can be
--reportor--report <path>If path is not provided, we do a best effort to infer based on the config / template name. For url endpoints, path is required.