mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
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.
58 lines
1.8 KiB
YAML
58 lines
1.8 KiB
YAML
version: 2
|
|
distribution_spec:
|
|
description: CI tests for Llama Stack
|
|
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::huggingface-cpu
|
|
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]
|