mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
feat(distro): fork off a starter-gpu distribution (#3240)
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.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
3b9278f254
commit
7519b73fcc
15 changed files with 522 additions and 31 deletions
238
llama_stack/distributions/starter-gpu/run.yaml
Normal file
238
llama_stack/distributions/starter-gpu/run.yaml
Normal file
|
|
@ -0,0 +1,238 @@
|
|||
version: 2
|
||||
image_name: starter-gpu
|
||||
apis:
|
||||
- agents
|
||||
- batches
|
||||
- datasetio
|
||||
- eval
|
||||
- files
|
||||
- inference
|
||||
- post_training
|
||||
- safety
|
||||
- scoring
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
|
||||
provider_type: remote::cerebras
|
||||
config:
|
||||
base_url: https://api.cerebras.ai
|
||||
api_key: ${env.CEREBRAS_API_KEY:=}
|
||||
- provider_id: ${env.OLLAMA_URL:+ollama}
|
||||
provider_type: remote::ollama
|
||||
config:
|
||||
url: ${env.OLLAMA_URL:=http://localhost:11434}
|
||||
- provider_id: ${env.VLLM_URL:+vllm}
|
||||
provider_type: remote::vllm
|
||||
config:
|
||||
url: ${env.VLLM_URL:=}
|
||||
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
|
||||
api_token: ${env.VLLM_API_TOKEN:=fake}
|
||||
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
|
||||
- provider_id: ${env.TGI_URL:+tgi}
|
||||
provider_type: remote::tgi
|
||||
config:
|
||||
url: ${env.TGI_URL:=}
|
||||
- provider_id: fireworks
|
||||
provider_type: remote::fireworks
|
||||
config:
|
||||
url: https://api.fireworks.ai/inference/v1
|
||||
api_key: ${env.FIREWORKS_API_KEY:=}
|
||||
- provider_id: together
|
||||
provider_type: remote::together
|
||||
config:
|
||||
url: https://api.together.xyz/v1
|
||||
api_key: ${env.TOGETHER_API_KEY:=}
|
||||
- provider_id: bedrock
|
||||
provider_type: remote::bedrock
|
||||
- provider_id: ${env.NVIDIA_API_KEY:+nvidia}
|
||||
provider_type: remote::nvidia
|
||||
config:
|
||||
url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
|
||||
api_key: ${env.NVIDIA_API_KEY:=}
|
||||
append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
|
||||
- provider_id: openai
|
||||
provider_type: remote::openai
|
||||
config:
|
||||
api_key: ${env.OPENAI_API_KEY:=}
|
||||
base_url: ${env.OPENAI_BASE_URL:=https://api.openai.com/v1}
|
||||
- provider_id: anthropic
|
||||
provider_type: remote::anthropic
|
||||
config:
|
||||
api_key: ${env.ANTHROPIC_API_KEY:=}
|
||||
- provider_id: gemini
|
||||
provider_type: remote::gemini
|
||||
config:
|
||||
api_key: ${env.GEMINI_API_KEY:=}
|
||||
- provider_id: ${env.VERTEX_AI_PROJECT:+vertexai}
|
||||
provider_type: remote::vertexai
|
||||
config:
|
||||
project: ${env.VERTEX_AI_PROJECT:=}
|
||||
location: ${env.VERTEX_AI_LOCATION:=us-central1}
|
||||
- provider_id: groq
|
||||
provider_type: remote::groq
|
||||
config:
|
||||
url: https://api.groq.com
|
||||
api_key: ${env.GROQ_API_KEY:=}
|
||||
- provider_id: sambanova
|
||||
provider_type: remote::sambanova
|
||||
config:
|
||||
url: https://api.sambanova.ai/v1
|
||||
api_key: ${env.SAMBANOVA_API_KEY:=}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
vector_io:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/faiss_store.db
|
||||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec_registry.db
|
||||
- provider_id: ${env.MILVUS_URL:+milvus}
|
||||
provider_type: inline::milvus
|
||||
config:
|
||||
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/milvus_registry.db
|
||||
- provider_id: ${env.CHROMADB_URL:+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter/}/chroma_remote_registry.db
|
||||
- provider_id: ${env.PGVECTOR_DB:+pgvector}
|
||||
provider_type: remote::pgvector
|
||||
config:
|
||||
host: ${env.PGVECTOR_HOST:=localhost}
|
||||
port: ${env.PGVECTOR_PORT:=5432}
|
||||
db: ${env.PGVECTOR_DB:=}
|
||||
user: ${env.PGVECTOR_USER:=}
|
||||
password: ${env.PGVECTOR_PASSWORD:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/pgvector_registry.db
|
||||
files:
|
||||
- provider_id: meta-reference-files
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
- provider_id: code-scanner
|
||||
provider_type: inline::code-scanner
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/responses_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/trace_store.db
|
||||
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
||||
post_training:
|
||||
- provider_id: torchtune-gpu
|
||||
provider_type: inline::torchtune-gpu
|
||||
config:
|
||||
checkpoint_format: meta
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/meta_reference_eval.db
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/localfs_datasetio.db
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
- provider_id: llm-as-judge
|
||||
provider_type: inline::llm-as-judge
|
||||
- provider_id: braintrust
|
||||
provider_type: inline::braintrust
|
||||
config:
|
||||
openai_api_key: ${env.OPENAI_API_KEY:=}
|
||||
tool_runtime:
|
||||
- provider_id: brave-search
|
||||
provider_type: remote::brave-search
|
||||
config:
|
||||
api_key: ${env.BRAVE_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: tavily-search
|
||||
provider_type: remote::tavily-search
|
||||
config:
|
||||
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: rag-runtime
|
||||
provider_type: inline::rag-runtime
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
batches:
|
||||
- provider_id: reference
|
||||
provider_type: inline::reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/batches.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/inference_store.db
|
||||
models: []
|
||||
shields:
|
||||
- shield_id: llama-guard
|
||||
provider_id: ${env.SAFETY_MODEL:+llama-guard}
|
||||
provider_shield_id: ${env.SAFETY_MODEL:=}
|
||||
- shield_id: code-scanner
|
||||
provider_id: ${env.CODE_SCANNER_MODEL:+code-scanner}
|
||||
provider_shield_id: ${env.CODE_SCANNER_MODEL:=}
|
||||
vector_dbs: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
benchmarks: []
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
- toolgroup_id: builtin::rag
|
||||
provider_id: rag-runtime
|
||||
server:
|
||||
port: 8321
|
||||
Loading…
Add table
Add a link
Reference in a new issue