mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-31 21:40:01 +00:00
59 lines
1.6 KiB
YAML
59 lines
1.6 KiB
YAML
inference:
|
|
tests:
|
|
- inference/test_vision_inference.py::test_vision_chat_completion_streaming
|
|
- inference/test_vision_inference.py::test_vision_chat_completion_non_streaming
|
|
- inference/test_text_inference.py::test_structured_output
|
|
- inference/test_text_inference.py::test_chat_completion_streaming
|
|
- inference/test_text_inference.py::test_chat_completion_non_streaming
|
|
- inference/test_text_inference.py::test_chat_completion_with_tool_calling
|
|
- inference/test_text_inference.py::test_chat_completion_with_tool_calling_streaming
|
|
|
|
fixtures:
|
|
provider_fixtures:
|
|
- inference: ollama
|
|
- default_fixture_param_id: fireworks
|
|
- inference: together
|
|
# - inference: tgi
|
|
# - inference: vllm_remote
|
|
inference_models:
|
|
- meta-llama/Llama-3.1-8B-Instruct
|
|
- meta-llama/Llama-3.2-11B-Vision-Instruct
|
|
|
|
safety_shield: ~
|
|
embedding_model: ~
|
|
|
|
|
|
agent:
|
|
tests:
|
|
- agents/test_agents.py::test_agent_turns_with_safety
|
|
- agents/test_agents.py::test_rag_agent
|
|
|
|
fixtures:
|
|
provider_fixtures:
|
|
- default_fixture_param_id: ollama
|
|
- default_fixture_param_id: together
|
|
- default_fixture_param_id: fireworks
|
|
|
|
safety_shield: ~
|
|
embedding_model: ~
|
|
|
|
inference_models:
|
|
- meta-llama/Llama-3.2-1B-Instruct
|
|
|
|
|
|
memory:
|
|
tests:
|
|
- memory/test_memory.py::test_query_documents
|
|
|
|
fixtures:
|
|
provider_fixtures:
|
|
- default_fixture_param_id: ollama
|
|
- inference: sentence_transformers
|
|
memory: faiss
|
|
- default_fixture_param_id: chroma
|
|
|
|
inference_models:
|
|
- meta-llama/Llama-3.2-1B-Instruct
|
|
|
|
safety_shield: ~
|
|
embedding_model: ~
|