mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-31 02:43:53 +00:00
6b9f673fdb
# Conflicts: # llama_stack/distribution/routers/routers.py # llama_stack/templates/ollama/build.yaml # llama_stack/templates/ollama/run-with-safety.yaml # llama_stack/templates/ollama/run.yaml # llama_stack/templates/remote-vllm/build.yaml # llama_stack/templates/remote-vllm/run-with-safety.yaml # llama_stack/templates/remote-vllm/run.yaml # llama_stack/templates/together/build.yaml # llama_stack/templates/together/run-with-safety.yaml # llama_stack/templates/together/run.yaml
37 lines
849 B
YAML
37 lines
849 B
YAML
version: '2'
|
|
distribution_spec:
|
|
description: Use Together.AI for running LLM inference
|
|
providers:
|
|
inference:
|
|
- remote::together
|
|
- inline::sentence-transformers
|
|
vector_io:
|
|
- inline::faiss
|
|
- remote::chromadb
|
|
- remote::pgvector
|
|
safety:
|
|
- inline::llama-guard
|
|
agents:
|
|
- inline::meta-reference
|
|
telemetry:
|
|
- inline::meta-reference
|
|
eval:
|
|
- inline::meta-reference
|
|
datasetio:
|
|
- remote::huggingface
|
|
- inline::localfs
|
|
scoring:
|
|
- inline::basic
|
|
- inline::llm-as-judge
|
|
- inline::braintrust
|
|
tool_runtime:
|
|
- remote::brave-search
|
|
- remote::tavily-search
|
|
- inline::code-interpreter
|
|
- inline::rag-runtime
|
|
- remote::model-context-protocol
|
|
- remote::wolfram-alpha
|
|
preprocessing:
|
|
- inline::basic
|
|
- inline::simple_chunking
|
|
image_type: conda
|