2f1da8ff62
test plan:
```
cat > custom-ollama-run.yaml
```
```yaml
version: 2
image_name: starter
external_providers_dir: /.llama/providers.d
apis:
- inference
- vector_io
- files
- safety
- tool_runtime
- agents
providers:
inference:
# Single Ollama provider for all models
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
persistence:
namespace: vector_io::faiss
backend: kv_default
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: /.llama/files
metadata_store:
table_name: files_metadata
backend: sql_default
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
tool_runtime:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence:
agent_state:
namespace: agents
backend: kv_default
responses:
table_name: responses
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
storage:
backends:
kv_default:
type: kv_sqlite
db_path: /.llama/kvstore.db
sql_default:
type: sql_sqlite
db_path: /.llama/sql_store.db
stores:
metadata:
namespace: registry
backend: kv_default
inference:
table_name: inference_store
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: sql_default
registered_resources:
models:
# All models use the same 'ollama' provider
- model_id: llama3.2-vision:latest
provider_id: ollama
provider_model_id: llama3.2-vision:latest
model_type: llm
- model_id: llama3.2:3b
provider_id: ollama
provider_model_id: llama3.2:3b
model_type: llm
# Embedding models
- model_id: nomic-embed-text-v2-moe
provider_id: ollama
provider_model_id: toshk0/nomic-embed-text-v2-moe:Q6_K
model_type: embedding
metadata:
embedding_dimension: 768
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups: []
server:
port: 8321
telemetry:
enabled: true
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: ollama
model_id: toshk0/nomic-embed-text-v2-moe:Q6_K
```
```bash
docker run
-it
--pull always
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT
-v ~/.llama:/root/.llama
-v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml
-e RUN_CONFIG_PATH=/app/custom-run.yaml
-e OLLAMA_URL=http://host.docker.internal:11434
llamastack/distribution-starter:0.3.0
--port $LLAMA_STACK_PORT
```
3.2 KiB
| orphan |
|---|
| true |
Meta Reference GPU Distribution
:maxdepth: 2
:hidden:
self
The llamastack/distribution-{{ name }} distribution consists of the following provider configurations:
{{ providers_table }}
Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs.
{% if run_config_env_vars %}
Environment Variables
The following environment variables can be configured:
{% for var, (default_value, description) in run_config_env_vars.items() %}
{{ var }}: {{ description }} (default:{{ default_value }}) {% endfor %} {% endif %}
Prerequisite: Downloading Models
Please check that you have llama model checkpoints downloaded in ~/.llama before proceeding. See installation guide here to download the models using the Hugging Face CLI.
## Running the Distribution
You can do this via venv 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.
```bash
LLAMA_STACK_PORT=8321
docker run \
-it \
--pull always \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT
If you are using Llama Stack Safety / Shield APIs, use:
docker run \
-it \
--pull always \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-e SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT
Via Docker with Custom Run Configuration
You can also run the Docker container with a custom run configuration file by mounting it into the container:
# Set the path to your custom run.yaml file
CUSTOM_RUN_CONFIG=/path/to/your/custom-run.yaml
LLAMA_STACK_PORT=8321
docker run \
-it \
--pull always \
--gpu all \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml \
-e RUN_CONFIG_PATH=/app/custom-run.yaml \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT
Note: The run configuration must be mounted into the container before it can be used. The -v flag mounts your local file into the container, and the RUN_CONFIG_PATH environment variable tells the entrypoint script which configuration to use.
{% if run_configs %} Available run configurations for this distribution: {% for config in run_configs %}
{{ config }}{% endfor %} {% endif %}
Via venv
Make sure you have the Llama Stack CLI available.
llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
llama stack run distributions/{{ name }}/run.yaml \
--port 8321
If you are using Llama Stack Safety / Shield APIs, use:
INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
llama stack run distributions/{{ name }}/run-with-safety.yaml \
--port 8321