mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-22 20:02:25 +00:00
bf610adf9b
Summary: ### THIS DIFF ### PLAN ### CONTEXT ### DESIGN Test Plan: # Test Setup **Type checker and check that the build compiles** **Unit Tests** **E2E Tests** // Screenshots and videos | Before | After | |--| | … | … | # Monitoring Plan.
49 lines
1.2 KiB
YAML
49 lines
1.2 KiB
YAML
|
|
inference:
|
|
providers:
|
|
- id: ollama
|
|
- id: together
|
|
env_param: TOGETHER_API_KEY
|
|
- id: fireworks
|
|
env_param: FIREWORKS_API_KEY
|
|
- id: tgi
|
|
- id: vllm
|
|
apis:
|
|
- chat_completion
|
|
- embeddings
|
|
capabilities:
|
|
- streaming
|
|
- tool_calling
|
|
- structured_output
|
|
model_tests:
|
|
- model_type: vision
|
|
model_name: meta-llama/Llama-3.2-11B-Vision-Instruct
|
|
test_path: /llama_stack/providers/tests/inference/test_vision_inference.py
|
|
test_api:
|
|
- chat_completion
|
|
test_capabilities:
|
|
- streaming
|
|
- model_type: text
|
|
model_name: meta-llama/Llama-3.1-8B-Instruct
|
|
test_path: /llama_stack/providers/tests/inference/test_text_inference.py
|
|
test_api:
|
|
- chat_completion
|
|
test_capabilities:
|
|
- streaming
|
|
- tool_calling
|
|
- structured_output
|
|
- model_type: embedding
|
|
model_name: sentence-transformers/all-MiniLM-L6-v2
|
|
test_path: /llama_stack/providers/tests/inference/test_embeddings.py
|
|
test_api:
|
|
- embedding
|
|
test_capabilities: ~
|
|
|
|
memory:
|
|
providers:
|
|
- faiss
|
|
- weaviate
|
|
- pgvector
|
|
- chroma
|
|
test_path:
|
|
- /llama_stack/providers/tests/memory/test_memory.py
|