mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-03 19:57:35 +00:00
7519b73fcc
The starter distribution added post-training which added torch dependencies which pulls in all the nvidia CUDA libraries. This made our starter container very big. We have worked hard to keep the starter container small so it serves its purpose as a starter. This PR tries to get it back to its size by forking off duplicate "-gpu" providers for post-training. These forked providers are then used for a new `starter-gpu` distribution which can pull in all dependencies.
59 lines
1.9 KiB
YAML
59 lines
1.9 KiB
YAML
version: 2
|
|
distribution_spec:
|
|
description: Quick start template for running Llama Stack with several popular providers.
|
|
This distribution is intended for GPU-enabled environments.
|
|
providers:
|
|
inference:
|
|
- provider_type: remote::cerebras
|
|
- provider_type: remote::ollama
|
|
- provider_type: remote::vllm
|
|
- provider_type: remote::tgi
|
|
- provider_type: remote::fireworks
|
|
- provider_type: remote::together
|
|
- provider_type: remote::bedrock
|
|
- provider_type: remote::nvidia
|
|
- provider_type: remote::openai
|
|
- provider_type: remote::anthropic
|
|
- provider_type: remote::gemini
|
|
- provider_type: remote::vertexai
|
|
- provider_type: remote::groq
|
|
- provider_type: remote::sambanova
|
|
- provider_type: inline::sentence-transformers
|
|
vector_io:
|
|
- provider_type: inline::faiss
|
|
- provider_type: inline::sqlite-vec
|
|
- provider_type: inline::milvus
|
|
- provider_type: remote::chromadb
|
|
- provider_type: remote::pgvector
|
|
files:
|
|
- provider_type: inline::localfs
|
|
safety:
|
|
- provider_type: inline::llama-guard
|
|
- provider_type: inline::code-scanner
|
|
agents:
|
|
- provider_type: inline::meta-reference
|
|
telemetry:
|
|
- provider_type: inline::meta-reference
|
|
post_training:
|
|
- provider_type: inline::torchtune-gpu
|
|
eval:
|
|
- provider_type: inline::meta-reference
|
|
datasetio:
|
|
- provider_type: remote::huggingface
|
|
- provider_type: inline::localfs
|
|
scoring:
|
|
- provider_type: inline::basic
|
|
- provider_type: inline::llm-as-judge
|
|
- provider_type: inline::braintrust
|
|
tool_runtime:
|
|
- provider_type: remote::brave-search
|
|
- provider_type: remote::tavily-search
|
|
- provider_type: inline::rag-runtime
|
|
- provider_type: remote::model-context-protocol
|
|
batches:
|
|
- provider_type: inline::reference
|
|
image_type: venv
|
|
additional_pip_packages:
|
|
- aiosqlite
|
|
- asyncpg
|
|
- sqlalchemy[asyncio]
|