phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 20:18:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into nvidia-e2e-notebook

Browse source
This commit is contained in:
Jash Gulabrai 2025-05-28 17:48:15 -04:00
commit f5cb965f0f
226 changed files with 16519 additions and 8666 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/templates/bedrock/build.yaml
View file

@ -29,3 +29,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/bedrock/run.yaml
View file

@ -35,6 +35,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -96,6 +99,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/inference_store.db
models:
- metadata: {}
model_id: meta.llama3-1-8b-instruct-v1:0

2
llama_stack/templates/cerebras/build.yaml
View file

@ -29,3 +29,5 @@ distribution_spec:
- remote::tavily-search
- inline::rag-runtime
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/cerebras/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/responses_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -99,6 +102,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/cerebras}/inference_store.db
models:
- metadata: {}
model_id: llama3.1-8b

2
llama_stack/templates/ci-tests/build.yaml
View file

@ -30,3 +30,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/ci-tests/run.yaml
View file

@ -38,6 +38,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -99,6 +102,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ci-tests}/inference_store.db
models:
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p1-8b-instruct

3
llama_stack/templates/dell/build.yaml
View file

@ -30,3 +30,6 @@ distribution_spec:
- remote::tavily-search
- inline::rag-runtime
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/dell/run-with-safety.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -99,6 +102,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/dell/run.yaml
View file

@ -37,6 +37,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -95,6 +98,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dell}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

843
llama_stack/templates/dependencies.json
View file

@ -1,843 +0,0 @@
{
"bedrock": [
"aiosqlite",
"autoevals",
"blobfile",
"boto3",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn"
],
"cerebras": [
"aiosqlite",
"autoevals",
"blobfile",
"cerebras_cloud_sdk",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"ci-tests": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"fireworks-ai",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"sqlite-vec",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"dell": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"fireworks": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"fireworks-ai",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"groq": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn"
],
"hf-endpoint": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn"
],
"hf-serverless": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"llama_api": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"sqlite-vec",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"meta-reference-gpu": [
"accelerate",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fairscale",
"faiss-cpu",
"fastapi",
"fbgemm-gpu-genai==1.1.2",
"fire",
"httpx",
"langdetect",
"lm-format-enforcer",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentence-transformers",
"sentencepiece",
"torch",
"torchao==0.8.0",
"torchvision",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"zmq"
],
"nvidia": [
"aiohttp",
"aiosqlite",
"blobfile",
"chardet",
"datasets",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"matplotlib",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn"
],
"ollama": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"ollama",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"peft",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"torch",
"tqdm",
"transformers",
"tree_sitter",
"trl",
"uvicorn"
],
"open-benchmark": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"sqlite-vec",
"together",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn"
],
"passthrough": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"remote-vllm": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"sambanova": [
"aiosqlite",
"blobfile",
"chardet",
"chromadb-client",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"litellm",
"matplotlib",
"mcp",
"nltk",
"numpy",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"starter": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"fireworks-ai",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"sqlite-vec",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"tgi": [
"aiohttp",
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"huggingface_hub",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"together": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"together",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"verification": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"fastapi",
"fire",
"httpx",
"langdetect",
"litellm",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"sqlite-vec",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"vllm-gpu": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"chromadb-client",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"vllm",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
],
"watsonx": [
"aiosqlite",
"autoevals",
"blobfile",
"chardet",
"datasets",
"emoji",
"faiss-cpu",
"fastapi",
"fire",
"httpx",
"ibm_watson_machine_learning",
"langdetect",
"matplotlib",
"mcp",
"nltk",
"numpy",
"openai",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-sdk",
"pandas",
"pillow",
"psycopg2-binary",
"pymongo",
"pypdf",
"pythainlp",
"redis",
"requests",
"scikit-learn",
"scipy",
"sentencepiece",
"tqdm",
"transformers",
"tree_sitter",
"uvicorn",
"sentence-transformers --no-deps",
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
]
}

3
llama_stack/templates/fireworks/build.yaml
View file

@ -31,3 +31,6 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/fireworks/run-with-safety.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -111,6 +114,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/inference_store.db
models:
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p1-8b-instruct

6
llama_stack/templates/fireworks/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -106,6 +109,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/fireworks}/inference_store.db
models:
- metadata: {}
model_id: accounts/fireworks/models/llama-v3p1-8b-instruct

2
llama_stack/templates/groq/build.yaml
View file

@ -26,3 +26,5 @@ distribution_spec:
- remote::tavily-search
- inline::rag-runtime
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/groq/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -99,6 +102,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/groq}/inference_store.db
models:
- metadata: {}
model_id: groq/llama3-8b-8192

3
llama_stack/templates/hf-endpoint/build.yaml
View file

@ -29,3 +29,6 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/hf-endpoint/run-with-safety.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -107,6 +110,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/hf-endpoint/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -102,6 +105,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

3
llama_stack/templates/hf-serverless/build.yaml
View file

@ -30,3 +30,6 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/hf-serverless/run-with-safety.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -107,6 +110,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/hf-serverless/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -102,6 +105,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

2
llama_stack/templates/llama_api/build.yaml
View file

@ -30,3 +30,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/llama_api/run.yaml
View file

@ -50,6 +50,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -111,6 +114,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/llama_api}/inference_store.db
models:
- metadata: {}
model_id: Llama-3.3-70B-Instruct

3
llama_stack/templates/meta-reference-gpu/build.yaml
View file

@ -29,3 +29,6 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
View file

@ -56,6 +56,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -117,6 +120,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/meta-reference-gpu/run.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -107,6 +110,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-gpu}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

3
llama_stack/templates/nvidia/build.yaml
View file

@ -24,3 +24,6 @@ distribution_spec:
tool_runtime:
- inline::rag-runtime
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/nvidia/run-with-safety.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -92,6 +95,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/nvidia/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -80,6 +83,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: meta/llama3-8b-instruct

3
llama_stack/templates/ollama/build.yaml
View file

@ -32,3 +32,6 @@ distribution_spec:
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/ollama/run-with-safety.yaml
View file

@ -40,6 +40,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -112,6 +115,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/ollama/run.yaml
View file

@ -38,6 +38,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -110,6 +113,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

2
llama_stack/templates/open-benchmark/build.yaml
View file

@ -33,3 +33,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/open-benchmark/run.yaml
View file

@ -64,6 +64,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -125,6 +128,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/inference_store.db
models:
- metadata: {}
model_id: openai/gpt-4o

3
llama_stack/templates/passthrough/build.yaml
View file

@ -31,3 +31,6 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/passthrough/run-with-safety.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -111,6 +114,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/inference_store.db
models:
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct

6
llama_stack/templates/passthrough/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -106,6 +109,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/passthrough}/inference_store.db
models:
- metadata: {}
model_id: meta-llama/Llama-3.1-8B-Instruct

3
llama_stack/templates/remote-vllm/build.yaml
View file

@ -31,3 +31,6 @@ distribution_spec:
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/remote-vllm/run-with-safety.yaml
View file

@ -50,6 +50,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/responses_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -115,6 +118,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/remote-vllm/run.yaml
View file

@ -43,6 +43,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/responses_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -108,6 +111,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/sambanova/build.yaml
View file

@ -1,6 +1,6 @@
version: '2'
distribution_spec:
description: Use SambaNova for running LLM inference
description: Use SambaNova for running LLM inference and safety
providers:
inference:
- remote::sambanova
@ -10,7 +10,7 @@ distribution_spec:
- remote::chromadb
- remote::pgvector
safety:
- inline::llama-guard
- remote::sambanova
agents:
- inline::meta-reference
telemetry:
@ -22,3 +22,5 @@ distribution_spec:
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

23
llama_stack/templates/sambanova/doc_template.md
View file

@ -37,33 +37,44 @@ The following models are available by default:
### Prerequisite: API Keys
Make sure you have access to a SambaNova API Key. You can get one by visiting [SambaNova.ai](https://sambanova.ai/).
Make sure you have access to a SambaNova API Key. You can get one by visiting [SambaNova.ai](http://cloud.sambanova.ai?utm_source=llamastack&utm_medium=external&utm_campaign=cloud_signup).
## Running Llama Stack with SambaNova
You can do this via Conda (build code) or Docker which has a pre-built image.
### Via Docker
This method allows you to get started quickly without having to build the distribution code.
### Via Docker
```bash
LLAMA_STACK_PORT=8321
llama stack build --template sambanova --image-type container
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
-v ~/.llama:/root/.llama \
distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
```
### Via Venv
```bash
llama stack build --template sambanova --image-type venv
llama stack run --image-type venv ~/.llama/distributions/sambanova/sambanova-run.yaml \
--port $LLAMA_STACK_PORT \
--env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
```
### Via Conda
```bash
llama stack build --template sambanova --image-type conda
llama stack run ./run.yaml \
llama stack run --image-type conda ~/.llama/distributions/sambanova/sambanova-run.yaml \
--port $LLAMA_STACK_PORT \
--env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
```

16
llama_stack/templates/sambanova/run.yaml
View file

@ -38,10 +38,11 @@ providers:
user: ${env.PGVECTOR_USER:}
password: ${env.PGVECTOR_PASSWORD:}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
- provider_id: sambanova
provider_type: remote::sambanova
config:
excluded_categories: []
url: https://api.sambanova.ai/v1
api_key: ${env.SAMBANOVA_API_KEY}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -50,6 +51,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -81,6 +85,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/inference_store.db
models:
- metadata: {}
model_id: sambanova/Meta-Llama-3.1-8B-Instruct
@ -189,6 +196,9 @@ models:
model_type: embedding
shields:
- shield_id: meta-llama/Llama-Guard-3-8B
provider_shield_id: sambanova/Meta-Llama-Guard-3-8B
- shield_id: sambanova/Meta-Llama-Guard-3-8B
provider_shield_id: sambanova/Meta-Llama-Guard-3-8B
vector_dbs: []
datasets: []
scoring_fns: []

14
llama_stack/templates/sambanova/sambanova.py
View file

@ -34,7 +34,7 @@ def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["remote::sambanova", "inline::sentence-transformers"],
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
"safety": ["inline::llama-guard"],
"safety": ["remote::sambanova"],
"agents": ["inline::meta-reference"],
"telemetry": ["inline::meta-reference"],
"tool_runtime": [
@ -110,7 +110,7 @@ def get_distribution_template() -> DistributionTemplate:
return DistributionTemplate(
name=name,
distro_type="self_hosted",
description="Use SambaNova for running LLM inference",
description="Use SambaNova for running LLM inference and safety",
container_image=None,
template_path=Path(__file__).parent / "doc_template.md",
providers=providers,
@ -122,7 +122,15 @@ def get_distribution_template() -> DistributionTemplate:
"vector_io": vector_io_providers,
},
default_models=default_models + [embedding_model],
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
default_shields=[
ShieldInput(
shield_id="meta-llama/Llama-Guard-3-8B", provider_shield_id="sambanova/Meta-Llama-Guard-3-8B"
),
ShieldInput(
shield_id="sambanova/Meta-Llama-Guard-3-8B",
provider_shield_id="sambanova/Meta-Llama-Guard-3-8B",
),
],
default_tool_groups=default_tool_groups,
),
},

2
llama_stack/templates/starter/build.yaml
View file

@ -35,3 +35,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/starter/run.yaml
View file

@ -72,6 +72,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -133,6 +136,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/starter}/inference_store.db
models:
- metadata: {}
model_id: openai/gpt-4o

13
llama_stack/templates/template.py
View file

@ -29,6 +29,7 @@ from llama_stack.distribution.distribution import get_provider_registry
from llama_stack.distribution.utils.dynamic import instantiate_class_type
from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
def get_model_registry(
@ -117,6 +118,10 @@ class RunConfigSettings(BaseModel):
__distro_dir__=f"~/.llama/distributions/{name}",
db_name="registry.db",
),
inference_store=SqliteSqlStoreConfig.sample_run_config(
__distro_dir__=f"~/.llama/distributions/{name}",
db_name="inference_store.db",
),
models=self.default_models or [],
shields=self.default_shields or [],
tool_groups=self.default_tool_groups or [],
@ -146,14 +151,20 @@ class DistributionTemplate(BaseModel):
available_models_by_provider: dict[str, list[ProviderModelEntry]] | None = None
def build_config(self) -> BuildConfig:
additional_pip_packages: list[str] = []
for run_config in self.run_configs.values():
run_config_ = run_config.run_config(self.name, self.providers, self.container_image)
if run_config_.inference_store:
additional_pip_packages.extend(run_config_.inference_store.pip_packages)
return BuildConfig(
name=self.name,
distribution_spec=DistributionSpec(
description=self.description,
container_image=self.container_image,
providers=self.providers,
),
image_type="conda", # default to conda, can be overridden
additional_pip_packages=additional_pip_packages,
)
def generate_markdown_docs(self) -> str:

3
llama_stack/templates/tgi/build.yaml
View file

@ -30,3 +30,6 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/tgi/run-with-safety.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -102,6 +105,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

6
llama_stack/templates/tgi/run.yaml
View file

@ -40,6 +40,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -101,6 +104,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/tgi}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

3
llama_stack/templates/together/build.yaml
View file

@ -31,3 +31,6 @@ distribution_spec:
- remote::model-context-protocol
- remote::wolfram-alpha
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

6
llama_stack/templates/together/run-with-safety.yaml
View file

@ -46,6 +46,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -111,6 +114,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/inference_store.db
models:
- metadata: {}
model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

6
llama_stack/templates/together/run.yaml
View file

@ -41,6 +41,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -106,6 +109,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/together}/inference_store.db
models:
- metadata: {}
model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

2
llama_stack/templates/verification/build.yaml
View file

@ -35,3 +35,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/verification/run.yaml
View file

@ -74,6 +74,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -135,6 +138,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/inference_store.db
models:
- metadata: {}
model_id: openai/gpt-4o

2
llama_stack/templates/vllm-gpu/build.yaml
View file

@ -30,3 +30,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/vllm-gpu/run.yaml
View file

@ -45,6 +45,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -106,6 +109,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

2
llama_stack/templates/watsonx/build.yaml
View file

@ -28,3 +28,5 @@ distribution_spec:
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]

6
llama_stack/templates/watsonx/run.yaml
View file

@ -42,6 +42,9 @@ providers:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/responses_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -103,6 +106,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/watsonx}/inference_store.db
models:
- metadata: {}
model_id: meta-llama/llama-3-3-70b-instruct