mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-02 16:54:42 +00:00
Merge branch 'main' into add-nvidia-inference-adapter
This commit is contained in:
Matthew Farrellee
commit
5fbfb9d854
92 changed files with 2145 additions and 678 deletions
|
|
@ -1,45 +0,0 @@
|
|||
version: '2'
|
||||
image_name: local
|
||||
name: bedrock
|
||||
docker_image: null
|
||||
conda_env: local
|
||||
apis:
|
||||
- shields
|
||||
- agents
|
||||
- models
|
||||
- memory
|
||||
- memory_banks
|
||||
- inference
|
||||
- safety
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: bedrock0
|
||||
provider_type: remote::bedrock
|
||||
config:
|
||||
aws_access_key_id: <AWS_ACCESS_KEY_ID>
|
||||
aws_secret_access_key: <AWS_SECRET_ACCESS_KEY>
|
||||
aws_session_token: <AWS_SESSION_TOKEN>
|
||||
region_name: <AWS_REGION>
|
||||
memory:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
safety:
|
||||
- provider_id: bedrock0
|
||||
provider_type: remote::bedrock
|
||||
config:
|
||||
aws_access_key_id: <AWS_ACCESS_KEY_ID>
|
||||
aws_secret_access_key: <AWS_SECRET_ACCESS_KEY>
|
||||
aws_session_token: <AWS_SESSION_TOKEN>
|
||||
region_name: <AWS_REGION>
|
||||
agents:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ~/.llama/runtime/kvstore.db
|
||||
telemetry:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
1
distributions/bedrock/run.yaml
Symbolic link
1
distributions/bedrock/run.yaml
Symbolic link
|
|
@ -0,0 +1 @@
|
|||
../../llama_stack/templates/bedrock/run.yaml
|
||||
|
|
@ -1 +0,0 @@
|
|||
../../llama_stack/templates/databricks/build.yaml
|
||||
|
|
@ -1,4 +1,32 @@
|
|||
{
|
||||
"hf-serverless": [
|
||||
"aiohttp",
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
"chardet",
|
||||
"chromadb-client",
|
||||
"faiss-cpu",
|
||||
"fastapi",
|
||||
"fire",
|
||||
"httpx",
|
||||
"huggingface_hub",
|
||||
"matplotlib",
|
||||
"nltk",
|
||||
"numpy",
|
||||
"pandas",
|
||||
"pillow",
|
||||
"psycopg2-binary",
|
||||
"pypdf",
|
||||
"redis",
|
||||
"scikit-learn",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
"uvicorn",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"together": [
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
|
|
@ -26,6 +54,33 @@
|
|||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"vllm-gpu": [
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
"chardet",
|
||||
"chromadb-client",
|
||||
"faiss-cpu",
|
||||
"fastapi",
|
||||
"fire",
|
||||
"httpx",
|
||||
"matplotlib",
|
||||
"nltk",
|
||||
"numpy",
|
||||
"pandas",
|
||||
"pillow",
|
||||
"psycopg2-binary",
|
||||
"pypdf",
|
||||
"redis",
|
||||
"scikit-learn",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
"uvicorn",
|
||||
"vllm",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"remote-vllm": [
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
|
|
@ -108,6 +163,33 @@
|
|||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"bedrock": [
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
"boto3",
|
||||
"chardet",
|
||||
"chromadb-client",
|
||||
"faiss-cpu",
|
||||
"fastapi",
|
||||
"fire",
|
||||
"httpx",
|
||||
"matplotlib",
|
||||
"nltk",
|
||||
"numpy",
|
||||
"pandas",
|
||||
"pillow",
|
||||
"psycopg2-binary",
|
||||
"pypdf",
|
||||
"redis",
|
||||
"scikit-learn",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
"uvicorn",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"meta-reference-gpu": [
|
||||
"accelerate",
|
||||
"aiosqlite",
|
||||
|
|
@ -140,6 +222,40 @@
|
|||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"meta-reference-quantized-gpu": [
|
||||
"accelerate",
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
"chardet",
|
||||
"chromadb-client",
|
||||
"fairscale",
|
||||
"faiss-cpu",
|
||||
"fastapi",
|
||||
"fbgemm-gpu",
|
||||
"fire",
|
||||
"httpx",
|
||||
"lm-format-enforcer",
|
||||
"matplotlib",
|
||||
"nltk",
|
||||
"numpy",
|
||||
"pandas",
|
||||
"pillow",
|
||||
"psycopg2-binary",
|
||||
"pypdf",
|
||||
"redis",
|
||||
"scikit-learn",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"torch",
|
||||
"torchao==0.5.0",
|
||||
"torchvision",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
"uvicorn",
|
||||
"zmq",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"ollama": [
|
||||
"aiohttp",
|
||||
"aiosqlite",
|
||||
|
|
@ -167,5 +283,33 @@
|
|||
"uvicorn",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
],
|
||||
"hf-endpoint": [
|
||||
"aiohttp",
|
||||
"aiosqlite",
|
||||
"blobfile",
|
||||
"chardet",
|
||||
"chromadb-client",
|
||||
"faiss-cpu",
|
||||
"fastapi",
|
||||
"fire",
|
||||
"httpx",
|
||||
"huggingface_hub",
|
||||
"matplotlib",
|
||||
"nltk",
|
||||
"numpy",
|
||||
"pandas",
|
||||
"pillow",
|
||||
"psycopg2-binary",
|
||||
"pypdf",
|
||||
"redis",
|
||||
"scikit-learn",
|
||||
"scipy",
|
||||
"sentencepiece",
|
||||
"tqdm",
|
||||
"transformers",
|
||||
"uvicorn",
|
||||
"sentence-transformers --no-deps",
|
||||
"torch --index-url https://download.pytorch.org/whl/cpu"
|
||||
]
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1 +0,0 @@
|
|||
../../llama_stack/templates/hf-endpoint/build.yaml
|
||||
|
|
@ -1 +0,0 @@
|
|||
../../llama_stack/templates/hf-serverless/build.yaml
|
||||
|
|
@ -1 +0,0 @@
|
|||
../../llama_stack/templates/ollama/build.yaml
|
||||
|
|
@ -1,48 +0,0 @@
|
|||
services:
|
||||
ollama:
|
||||
image: ollama/ollama:latest
|
||||
network_mode: "host"
|
||||
volumes:
|
||||
- ollama:/root/.ollama # this solution synchronizes with the docker volume and loads the model rocket fast
|
||||
ports:
|
||||
- "11434:11434"
|
||||
devices:
|
||||
- nvidia.com/gpu=all
|
||||
environment:
|
||||
- CUDA_VISIBLE_DEVICES=0
|
||||
command: []
|
||||
deploy:
|
||||
resources:
|
||||
reservations:
|
||||
devices:
|
||||
- driver: nvidia
|
||||
# that's the closest analogue to --gpus; provide
|
||||
# an integer amount of devices or 'all'
|
||||
count: 1
|
||||
# Devices are reserved using a list of capabilities, making
|
||||
# capabilities the only required field. A device MUST
|
||||
# satisfy all the requested capabilities for a successful
|
||||
# reservation.
|
||||
capabilities: [gpu]
|
||||
runtime: nvidia
|
||||
llamastack:
|
||||
depends_on:
|
||||
- ollama
|
||||
image: llamastack/distribution-ollama
|
||||
network_mode: "host"
|
||||
volumes:
|
||||
- ~/.llama:/root/.llama
|
||||
# Link to ollama run.yaml file
|
||||
- ./run.yaml:/root/llamastack-run-ollama.yaml
|
||||
ports:
|
||||
- "5000:5000"
|
||||
# Hack: wait for ollama server to start before starting docker
|
||||
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-ollama.yaml"
|
||||
deploy:
|
||||
restart_policy:
|
||||
condition: on-failure
|
||||
delay: 3s
|
||||
max_attempts: 5
|
||||
window: 60s
|
||||
volumes:
|
||||
ollama:
|
||||
|
|
@ -1,46 +0,0 @@
|
|||
version: '2'
|
||||
image_name: local
|
||||
docker_image: null
|
||||
conda_env: local
|
||||
apis:
|
||||
- shields
|
||||
- agents
|
||||
- models
|
||||
- memory
|
||||
- memory_banks
|
||||
- inference
|
||||
- safety
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: ollama
|
||||
provider_type: remote::ollama
|
||||
config:
|
||||
url: ${env.OLLAMA_URL:http://127.0.0.1:11434}
|
||||
safety:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
memory:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ~/.llama/runtime/kvstore.db
|
||||
telemetry:
|
||||
- provider_id: meta0
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
models:
|
||||
- model_id: ${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}
|
||||
provider_id: ollama
|
||||
- model_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}
|
||||
provider_id: ollama
|
||||
shields:
|
||||
- shield_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}
|
||||
1
docs/.gitignore
vendored
Normal file
1
docs/.gitignore
vendored
Normal file
|
|
@ -0,0 +1 @@
|
|||
src
|
||||
139
docs/source/distributions/index.md
Normal file
139
docs/source/distributions/index.md
Normal file
|
|
@ -0,0 +1,139 @@
|
|||
# Llama Stack Distributions
|
||||
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self_hosted_distro/index
|
||||
remote_hosted_distro/index
|
||||
ondevice_distro/index
|
||||
```
|
||||
## Introduction
|
||||
|
||||
Llama Stack Distributions are pre-built Docker containers/Conda environments that assemble APIs and Providers to provide a consistent whole to the end application developer.
|
||||
These distributions allow you to mix-and-match providers - some could be backed by local code and some could be remote. This flexibility enables you to choose the optimal setup for your use case, such as serving a small model locally while using a cloud provider for larger models, all while maintaining a consistent API interface for your application.
|
||||
|
||||
|
||||
## Decide Your Build Type
|
||||
There are two ways to start a Llama Stack:
|
||||
|
||||
- **Docker**: we provide a number of pre-built Docker containers allowing you to get started instantly. If you are focused on application development, we recommend this option.
|
||||
- **Conda**: the `llama` CLI provides a simple set of commands to build, configure and run a Llama Stack server containing the exact combination of providers you wish. We have provided various templates to make getting started easier.
|
||||
|
||||
Both of these provide options to run model inference using our reference implementations, Ollama, TGI, vLLM or even remote providers like Fireworks, Together, Bedrock, etc.
|
||||
|
||||
### Decide Your Inference Provider
|
||||
|
||||
Running inference on the underlying Llama model is one of the most critical requirements. Depending on what hardware you have available, you have various options. Note that each option have different necessary prerequisites.
|
||||
|
||||
- **Do you have access to a machine with powerful GPUs?**
|
||||
If so, we suggest:
|
||||
- [distribution-meta-reference-gpu](./self_hosted_distro/meta-reference-gpu.md)
|
||||
- [distribution-tgi](./self_hosted_distro/tgi.md)
|
||||
|
||||
- **Are you running on a "regular" desktop machine?**
|
||||
If so, we suggest:
|
||||
- [distribution-ollama](./self_hosted_distro/ollama.md)
|
||||
|
||||
- **Do you have an API key for a remote inference provider like Fireworks, Together, etc.?** If so, we suggest:
|
||||
- [distribution-together](./remote_hosted_distro/together.md)
|
||||
- [distribution-fireworks](./remote_hosted_distro/fireworks.md)
|
||||
|
||||
- **Do you want to run Llama Stack inference on your iOS / Android device** If so, we suggest:
|
||||
- [iOS](./ondevice_distro/ios_sdk.md)
|
||||
- [Android](https://github.com/meta-llama/llama-stack-client-kotlin) (coming soon)
|
||||
|
||||
Please see our pages in detail for the types of distributions we offer:
|
||||
|
||||
1. [Self-Hosted Distributions](./self_hosted_distro/index.md): If you want to run Llama Stack inference on your local machine.
|
||||
2. [Remote-Hosted Distributions](./remote_hosted_distro/index.md): If you want to connect to a remote hosted inference provider.
|
||||
3. [On-device Distributions](./ondevice_distro/index.md): If you want to run Llama Stack inference on your iOS / Android device.
|
||||
|
||||
## Building Your Own Distribution
|
||||
|
||||
### Prerequisites
|
||||
|
||||
```bash
|
||||
$ git clone git@github.com:meta-llama/llama-stack.git
|
||||
```
|
||||
|
||||
|
||||
### Starting the Distribution
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} meta-reference-gpu
|
||||
##### System Requirements
|
||||
Access to Single-Node GPU to start a local server.
|
||||
|
||||
##### Downloading Models
|
||||
Please make sure you have Llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](../cli_reference/download_models.md) here to download the models.
|
||||
|
||||
```
|
||||
$ ls ~/.llama/checkpoints
|
||||
Llama3.1-8B Llama3.2-11B-Vision-Instruct Llama3.2-1B-Instruct Llama3.2-90B-Vision-Instruct Llama-Guard-3-8B
|
||||
Llama3.1-8B-Instruct Llama3.2-1B Llama3.2-3B-Instruct Llama-Guard-3-1B Prompt-Guard-86M
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} vLLM
|
||||
##### System Requirements
|
||||
Access to Single-Node GPU to start a vLLM server.
|
||||
:::
|
||||
|
||||
:::{tab-item} tgi
|
||||
##### System Requirements
|
||||
Access to Single-Node GPU to start a TGI server.
|
||||
:::
|
||||
|
||||
:::{tab-item} ollama
|
||||
##### System Requirements
|
||||
Access to Single-Node CPU/GPU able to run ollama.
|
||||
:::
|
||||
|
||||
:::{tab-item} together
|
||||
##### System Requirements
|
||||
Access to Single-Node CPU with Together hosted endpoint via API_KEY from [together.ai](https://api.together.xyz/signin).
|
||||
:::
|
||||
|
||||
:::{tab-item} fireworks
|
||||
##### System Requirements
|
||||
Access to Single-Node CPU with Fireworks hosted endpoint via API_KEY from [fireworks.ai](https://fireworks.ai/).
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} meta-reference-gpu
|
||||
- [Start Meta Reference GPU Distribution](./self_hosted_distro/meta-reference-gpu.md)
|
||||
:::
|
||||
|
||||
:::{tab-item} vLLM
|
||||
- [Start vLLM Distribution](./self_hosted_distro/remote-vllm.md)
|
||||
:::
|
||||
|
||||
:::{tab-item} tgi
|
||||
- [Start TGI Distribution](./self_hosted_distro/tgi.md)
|
||||
:::
|
||||
|
||||
:::{tab-item} ollama
|
||||
- [Start Ollama Distribution](./self_hosted_distro/ollama.md)
|
||||
:::
|
||||
|
||||
:::{tab-item} together
|
||||
- [Start Together Distribution](./self_hosted_distro/together.md)
|
||||
:::
|
||||
|
||||
:::{tab-item} fireworks
|
||||
- [Start Fireworks Distribution](./self_hosted_distro/fireworks.md)
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
### Troubleshooting
|
||||
|
||||
- If you encounter any issues, search through our [GitHub Issues](https://github.com/meta-llama/llama-stack/issues), or file an new issue.
|
||||
- Use `--port <PORT>` flag to use a different port number. For docker run, update the `-p <PORT>:<PORT>` flag.
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
# On-Device Distribution
|
||||
# On-Device Distributions
|
||||
|
||||
On-device distributions are Llama Stack distributions that run locally on your iOS / Android device.
|
||||
|
||||
|
|
@ -1,4 +1,11 @@
|
|||
# Remote-Hosted Distribution
|
||||
# Remote-Hosted Distributions
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
remote
|
||||
```
|
||||
|
||||
Remote-Hosted distributions are available endpoints serving Llama Stack API that you can directly connect to.
|
||||
|
||||
64
docs/source/distributions/self_hosted_distro/bedrock.md
Normal file
64
docs/source/distributions/self_hosted_distro/bedrock.md
Normal file
|
|
@ -0,0 +1,64 @@
|
|||
# Bedrock Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-bedrock` distribution consists of the following provider configurations:
|
||||
|
||||
| API | Provider(s) |
|
||||
|-----|-------------|
|
||||
| agents | `inline::meta-reference` |
|
||||
| inference | `remote::bedrock` |
|
||||
| memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
|
||||
| safety | `remote::bedrock` |
|
||||
| telemetry | `inline::meta-reference` |
|
||||
|
||||
|
||||
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
|
||||
|
||||
|
||||
|
||||
### Prerequisite: API Keys
|
||||
|
||||
Make sure you have access to a AWS Bedrock API Key. You can get one by visiting [AWS Bedrock](https://aws.amazon.com/bedrock/).
|
||||
|
||||
|
||||
## Running Llama Stack with AWS Bedrock
|
||||
|
||||
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.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=5001
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-bedrock \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
|
||||
--env AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
|
||||
--env AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
```bash
|
||||
llama stack build --template bedrock --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
|
||||
--env AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
|
||||
--env AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN
|
||||
```
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Dell-TGI Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-tgi` distribution consists of the following provider configurations.
|
||||
|
||||
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Fireworks Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-fireworks` distribution consists of the following provider configurations.
|
||||
|
||||
| API | Provider(s) |
|
||||
|
|
@ -51,9 +58,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-fireworks \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
|
||||
```
|
||||
|
|
@ -63,6 +68,6 @@ docker run \
|
|||
```bash
|
||||
llama stack build --template fireworks --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port 5001 \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
|
||||
```
|
||||
|
|
@ -1,20 +1,8 @@
|
|||
# Self-Hosted Distribution
|
||||
|
||||
We offer deployable distributions where you can host your own Llama Stack server using local inference.
|
||||
|
||||
| **Distribution** | **Llama Stack Docker** | Start This Distribution | **Inference** | **Agents** | **Memory** | **Safety** | **Telemetry** |
|
||||
|:----------------: |:------------------------------------------: |:-----------------------: |:------------------: |:------------------: |:------------------: |:------------------: |:------------------: |
|
||||
| Meta Reference | [llamastack/distribution-meta-reference-gpu](https://hub.docker.com/repository/docker/llamastack/distribution-meta-reference-gpu/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-gpu.html) | meta-reference | meta-reference | meta-reference; remote::pgvector; remote::chromadb | meta-reference | meta-reference |
|
||||
| Meta Reference Quantized | [llamastack/distribution-meta-reference-quantized-gpu](https://hub.docker.com/repository/docker/llamastack/distribution-meta-reference-quantized-gpu/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-quantized-gpu.html) | meta-reference-quantized | meta-reference | meta-reference; remote::pgvector; remote::chromadb | meta-reference | meta-reference |
|
||||
| Ollama | [llamastack/distribution-ollama](https://hub.docker.com/repository/docker/llamastack/distribution-ollama/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/ollama.html) | remote::ollama | meta-reference | remote::pgvector; remote::chromadb | meta-reference | meta-reference |
|
||||
| TGI | [llamastack/distribution-tgi](https://hub.docker.com/repository/docker/llamastack/distribution-tgi/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/tgi.html) | remote::tgi | meta-reference | meta-reference; remote::pgvector; remote::chromadb | meta-reference | meta-reference |
|
||||
| Together | [llamastack/distribution-together](https://hub.docker.com/repository/docker/llamastack/distribution-together/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/together.html) | remote::together | meta-reference | remote::weaviate | meta-reference | meta-reference |
|
||||
| Fireworks | [llamastack/distribution-fireworks](https://hub.docker.com/repository/docker/llamastack/distribution-fireworks/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/fireworks.html) | remote::fireworks | meta-reference | remote::weaviate | meta-reference | meta-reference |
|
||||
| Bedrock | [llamastack/distribution-bedrock](https://hub.docker.com/repository/docker/llamastack/distribution-bedrock/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/bedrock.html) | remote::bedrock | meta-reference | remote::weaviate | meta-reference | meta-reference |
|
||||
|
||||
# Self-Hosted Distributions
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 1
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
meta-reference-gpu
|
||||
meta-reference-quantized-gpu
|
||||
|
|
@ -26,3 +14,15 @@ fireworks
|
|||
remote-vllm
|
||||
bedrock
|
||||
```
|
||||
|
||||
We offer deployable distributions where you can host your own Llama Stack server using local inference.
|
||||
|
||||
| **Distribution** | **Llama Stack Docker** | Start This Distribution |
|
||||
|:----------------: |:------------------------------------------: |:-----------------------: |
|
||||
| Meta Reference | [llamastack/distribution-meta-reference-gpu](https://hub.docker.com/repository/docker/llamastack/distribution-meta-reference-gpu/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-gpu.html) |
|
||||
| Meta Reference Quantized | [llamastack/distribution-meta-reference-quantized-gpu](https://hub.docker.com/repository/docker/llamastack/distribution-meta-reference-quantized-gpu/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-quantized-gpu.html) |
|
||||
| Ollama | [llamastack/distribution-ollama](https://hub.docker.com/repository/docker/llamastack/distribution-ollama/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/ollama.html) |
|
||||
| TGI | [llamastack/distribution-tgi](https://hub.docker.com/repository/docker/llamastack/distribution-tgi/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/tgi.html) |
|
||||
| Together | [llamastack/distribution-together](https://hub.docker.com/repository/docker/llamastack/distribution-together/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/together.html) |
|
||||
| Fireworks | [llamastack/distribution-fireworks](https://hub.docker.com/repository/docker/llamastack/distribution-fireworks/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/fireworks.html) |
|
||||
| Bedrock | [llamastack/distribution-bedrock](https://hub.docker.com/repository/docker/llamastack/distribution-bedrock/general) | [Guide](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/bedrock.html) |
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Meta Reference Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-meta-reference-gpu` distribution consists of the following provider configurations:
|
||||
|
||||
| API | Provider(s) |
|
||||
|
|
@ -47,9 +54,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-meta-reference-gpu \
|
||||
/root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
|
@ -60,9 +65,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run-with-safety.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-meta-reference-gpu \
|
||||
/root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
|
|
@ -74,7 +77,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
|
|||
|
||||
```bash
|
||||
llama stack build --template meta-reference-gpu --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
llama stack run distributions/meta-reference-gpu/run.yaml \
|
||||
--port 5001 \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
|
@ -82,7 +85,7 @@ llama stack run ./run.yaml \
|
|||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run ./run-with-safety.yaml \
|
||||
llama stack run distributions/meta-reference-gpu/run-with-safety.yaml \
|
||||
--port 5001 \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
|
|
@ -0,0 +1,92 @@
|
|||
# Meta Reference Quantized Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists of the following provider configurations:
|
||||
|
||||
| API | Provider(s) |
|
||||
|-----|-------------|
|
||||
| agents | `inline::meta-reference` |
|
||||
| inference | `inline::meta-reference-quantized` |
|
||||
| memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
|
||||
| safety | `inline::llama-guard` |
|
||||
| telemetry | `inline::meta-reference` |
|
||||
|
||||
|
||||
The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc.
|
||||
|
||||
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.
|
||||
|
||||
### Environment Variables
|
||||
|
||||
The following environment variables can be configured:
|
||||
|
||||
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
|
||||
- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `meta-llama/Llama-3.2-3B-Instruct`)
|
||||
- `INFERENCE_CHECKPOINT_DIR`: Directory containing the Meta Reference model checkpoint (default: `null`)
|
||||
|
||||
|
||||
## Prerequisite: Downloading Models
|
||||
|
||||
Please make sure you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/cli_reference/download_models.html) here to download the models. Run `llama model list` to see the available models to download, and `llama model download` to download the checkpoints.
|
||||
|
||||
```
|
||||
$ ls ~/.llama/checkpoints
|
||||
Llama3.1-8B Llama3.2-11B-Vision-Instruct Llama3.2-1B-Instruct Llama3.2-90B-Vision-Instruct Llama-Guard-3-8B
|
||||
Llama3.1-8B-Instruct Llama3.2-1B Llama3.2-3B-Instruct Llama-Guard-3-1B Prompt-Guard-86M
|
||||
```
|
||||
|
||||
## Running the Distribution
|
||||
|
||||
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.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=5001
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-meta-reference-quantized-gpu \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-meta-reference-quantized-gpu \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
|
||||
|
||||
```bash
|
||||
llama stack build --template meta-reference-quantized-gpu --image-type conda
|
||||
llama stack run distributions/meta-reference-quantized-gpu/run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run distributions/meta-reference-quantized-gpu/run-with-safety.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
```
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Ollama Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-ollama` distribution consists of the following provider configurations.
|
||||
|
||||
| API | Provider(s) |
|
||||
|
|
@ -59,9 +66,7 @@ docker run \
|
|||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-ollama \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env OLLAMA_URL=http://host.docker.internal:11434
|
||||
|
|
@ -1,4 +1,10 @@
|
|||
# Remote vLLM Distribution
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-remote-vllm` distribution consists of the following provider configurations:
|
||||
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# TGI Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-tgi` distribution consists of the following provider configurations.
|
||||
|
||||
| API | Provider(s) |
|
||||
|
|
@ -78,9 +85,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-tgi \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT
|
||||
|
|
@ -109,18 +114,18 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
|
|||
```bash
|
||||
llama stack build --template tgi --image-type conda
|
||||
llama stack run ./run.yaml
|
||||
--port 5001
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run ./run-with-safety.yaml
|
||||
--port 5001
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL
|
||||
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT
|
||||
--env SAFETY_MODEL=$SAFETY_MODEL
|
||||
llama stack run ./run-with-safety.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT \
|
||||
--env SAFETY_MODEL=$SAFETY_MODEL \
|
||||
--env TGI_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT
|
||||
```
|
||||
|
|
@ -1,4 +1,11 @@
|
|||
# Fireworks Distribution
|
||||
# Together Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-together` distribution consists of the following provider configurations.
|
||||
|
||||
|
|
@ -50,9 +57,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-together \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env TOGETHER_API_KEY=$TOGETHER_API_KEY
|
||||
```
|
||||
|
|
@ -62,6 +67,6 @@ docker run \
|
|||
```bash
|
||||
llama stack build --template together --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port 5001 \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env TOGETHER_API_KEY=$TOGETHER_API_KEY
|
||||
```
|
||||
|
|
@ -1,58 +0,0 @@
|
|||
# Bedrock Distribution
|
||||
|
||||
### Connect to a Llama Stack Bedrock Endpoint
|
||||
- You may connect to Amazon Bedrock APIs for running LLM inference
|
||||
|
||||
The `llamastack/distribution-bedrock` distribution consists of the following provider configurations.
|
||||
|
||||
|
||||
| **API** | **Inference** | **Agents** | **Memory** | **Safety** | **Telemetry** |
|
||||
|----------------- |--------------- |---------------- |---------------- |---------------- |---------------- |
|
||||
| **Provider(s)** | remote::bedrock | meta-reference | meta-reference | remote::bedrock | meta-reference |
|
||||
|
||||
|
||||
### Docker: Start the Distribution (Single Node CPU)
|
||||
|
||||
> [!NOTE]
|
||||
> This assumes you have valid AWS credentials configured with access to Amazon Bedrock.
|
||||
|
||||
```
|
||||
$ cd distributions/bedrock && docker compose up
|
||||
```
|
||||
|
||||
Make sure in your `run.yaml` file, your inference provider is pointing to the correct AWS configuration. E.g.
|
||||
```
|
||||
inference:
|
||||
- provider_id: bedrock0
|
||||
provider_type: remote::bedrock
|
||||
config:
|
||||
aws_access_key_id: <AWS_ACCESS_KEY_ID>
|
||||
aws_secret_access_key: <AWS_SECRET_ACCESS_KEY>
|
||||
aws_session_token: <AWS_SESSION_TOKEN>
|
||||
region_name: <AWS_REGION>
|
||||
```
|
||||
|
||||
### Conda llama stack run (Single Node CPU)
|
||||
|
||||
```bash
|
||||
llama stack build --template bedrock --image-type conda
|
||||
# -- modify run.yaml with valid AWS credentials
|
||||
llama stack run ./run.yaml
|
||||
```
|
||||
|
||||
### (Optional) Update Model Serving Configuration
|
||||
|
||||
Use `llama-stack-client models list` to check the available models served by Amazon Bedrock.
|
||||
|
||||
```
|
||||
$ llama-stack-client models list
|
||||
+------------------------------+------------------------------+---------------+------------+
|
||||
| identifier | llama_model | provider_id | metadata |
|
||||
+==============================+==============================+===============+============+
|
||||
| Llama3.1-8B-Instruct | meta.llama3-1-8b-instruct-v1:0 | bedrock0 | {} |
|
||||
+------------------------------+------------------------------+---------------+------------+
|
||||
| Llama3.1-70B-Instruct | meta.llama3-1-70b-instruct-v1:0 | bedrock0 | {} |
|
||||
+------------------------------+------------------------------+---------------+------------+
|
||||
| Llama3.1-405B-Instruct | meta.llama3-1-405b-instruct-v1:0 | bedrock0 | {} |
|
||||
+------------------------------+------------------------------+---------------+------------+
|
||||
```
|
||||
|
|
@ -1,54 +0,0 @@
|
|||
# Meta Reference Quantized Distribution
|
||||
|
||||
The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists of the following provider configurations.
|
||||
|
||||
|
||||
| **API** | **Inference** | **Agents** | **Memory** | **Safety** | **Telemetry** |
|
||||
|----------------- |------------------------ |---------------- |-------------------------------------------------- |---------------- |---------------- |
|
||||
| **Provider(s)** | meta-reference-quantized | meta-reference | meta-reference, remote::pgvector, remote::chroma | meta-reference | meta-reference |
|
||||
|
||||
The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc.
|
||||
|
||||
### Step 0. Prerequisite - Downloading Models
|
||||
Please make sure you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/cli_reference/download_models.html) here to download the models.
|
||||
|
||||
```
|
||||
$ ls ~/.llama/checkpoints
|
||||
Llama3.2-3B-Instruct:int4-qlora-eo8
|
||||
```
|
||||
|
||||
### Step 1. Start the Distribution
|
||||
#### (Option 1) Start with Docker
|
||||
```
|
||||
$ cd distributions/meta-reference-quantized-gpu && docker compose up
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> This assumes you have access to GPU to start a local server with access to your GPU.
|
||||
|
||||
|
||||
> [!NOTE]
|
||||
> `~/.llama` should be the path containing downloaded weights of Llama models.
|
||||
|
||||
|
||||
This will download and start running a pre-built docker container. Alternatively, you may use the following commands:
|
||||
|
||||
```
|
||||
docker run -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./run.yaml:/root/my-run.yaml --gpus=all distribution-meta-reference-quantized-gpu --yaml_config /root/my-run.yaml
|
||||
```
|
||||
|
||||
#### (Option 2) Start with Conda
|
||||
|
||||
1. Install the `llama` CLI. See [CLI Reference](https://llama-stack.readthedocs.io/en/latest/cli_reference/index.html)
|
||||
|
||||
2. Build the `meta-reference-quantized-gpu` distribution
|
||||
|
||||
```
|
||||
$ llama stack build --template meta-reference-quantized-gpu --image-type conda
|
||||
```
|
||||
|
||||
3. Start running distribution
|
||||
```
|
||||
$ cd distributions/meta-reference-quantized-gpu
|
||||
$ llama stack run ./run.yaml
|
||||
```
|
||||
|
|
@ -1,194 +1,208 @@
|
|||
# Getting Started
|
||||
# Getting Started with Llama Stack
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
distributions/self_hosted_distro/index
|
||||
distributions/remote_hosted_distro/index
|
||||
distributions/ondevice_distro/index
|
||||
In this guide, we'll walk through using ollama as the inference provider and build a simple python application that uses the Llama Stack Client SDK
|
||||
|
||||
Llama stack consists of a distribution server and an accompanying client SDK. The distribution server can be configured for different providers for inference, memory, agents, evals etc. This configuration is defined in a yaml file called `run.yaml`.
|
||||
|
||||
Running inference on the underlying Llama model is one of the most critical requirements. Depending on what hardware you have available, you have various options. Note that each option have different necessary prerequisites. We will use ollama as the inference provider as it is the easiest to get started with.
|
||||
|
||||
### Step 1. Start the inference server
|
||||
```bash
|
||||
export LLAMA_STACK_PORT=5001
|
||||
export INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct"
|
||||
# ollama names this model differently, and we must use the ollama name when loading the model
|
||||
export OLLAMA_INFERENCE_MODEL="llama3.2:3b-instruct-fp16"
|
||||
ollama run $OLLAMA_INFERENCE_MODEL --keepalive 60m
|
||||
```
|
||||
|
||||
At the end of the guide, you will have learned how to:
|
||||
- get a Llama Stack server up and running
|
||||
- set up an agent (with tool-calling and vector stores) that works with the above server
|
||||
|
||||
To see more example apps built using Llama Stack, see [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main).
|
||||
|
||||
## Step 1. Starting Up Llama Stack Server
|
||||
|
||||
### Decide Your Build Type
|
||||
There are two ways to start a Llama Stack:
|
||||
|
||||
- **Docker**: we provide a number of pre-built Docker containers allowing you to get started instantly. If you are focused on application development, we recommend this option.
|
||||
- **Conda**: the `llama` CLI provides a simple set of commands to build, configure and run a Llama Stack server containing the exact combination of providers you wish. We have provided various templates to make getting started easier.
|
||||
|
||||
Both of these provide options to run model inference using our reference implementations, Ollama, TGI, vLLM or even remote providers like Fireworks, Together, Bedrock, etc.
|
||||
|
||||
### Decide Your Inference Provider
|
||||
|
||||
Running inference on the underlying Llama model is one of the most critical requirements. Depending on what hardware you have available, you have various options. Note that each option have different necessary prerequisites.
|
||||
|
||||
- **Do you have access to a machine with powerful GPUs?**
|
||||
If so, we suggest:
|
||||
- [distribution-meta-reference-gpu](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-gpu.html)
|
||||
- [distribution-tgi](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/tgi.html)
|
||||
|
||||
- **Are you running on a "regular" desktop machine?**
|
||||
If so, we suggest:
|
||||
- [distribution-ollama](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/ollama.html)
|
||||
|
||||
- **Do you have an API key for a remote inference provider like Fireworks, Together, etc.?** If so, we suggest:
|
||||
- [distribution-together](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/remote_hosted_distro/together.html)
|
||||
- [distribution-fireworks](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/remote_hosted_distro/fireworks.html)
|
||||
|
||||
- **Do you want to run Llama Stack inference on your iOS / Android device** If so, we suggest:
|
||||
- [iOS](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/ondevice_distro/ios_sdk.html)
|
||||
- [Android](https://github.com/meta-llama/llama-stack-client-kotlin) (coming soon)
|
||||
|
||||
Please see our pages in detail for the types of distributions we offer:
|
||||
|
||||
1. [Self-Hosted Distribution](./distributions/self_hosted_distro/index.md): If you want to run Llama Stack inference on your local machine.
|
||||
2. [Remote-Hosted Distribution](./distributions/remote_hosted_distro/index.md): If you want to connect to a remote hosted inference provider.
|
||||
3. [On-device Distribution](./distributions/ondevice_distro/index.md): If you want to run Llama Stack inference on your iOS / Android device.
|
||||
|
||||
|
||||
### Table of Contents
|
||||
|
||||
Once you have decided on the inference provider and distribution to use, use the following guides to get started.
|
||||
|
||||
##### 1.0 Prerequisite
|
||||
|
||||
```
|
||||
$ git clone git@github.com:meta-llama/llama-stack.git
|
||||
```
|
||||
|
||||
::::{tab-set}
|
||||
|
||||
:::{tab-item} meta-reference-gpu
|
||||
##### System Requirements
|
||||
Access to Single-Node GPU to start a local server.
|
||||
|
||||
##### Downloading Models
|
||||
Please make sure you have Llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/cli_reference/download_models.html) here to download the models.
|
||||
|
||||
```
|
||||
$ ls ~/.llama/checkpoints
|
||||
Llama3.1-8B Llama3.2-11B-Vision-Instruct Llama3.2-1B-Instruct Llama3.2-90B-Vision-Instruct Llama-Guard-3-8B
|
||||
Llama3.1-8B-Instruct Llama3.2-1B Llama3.2-3B-Instruct Llama-Guard-3-1B Prompt-Guard-86M
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::{tab-item} vLLM
|
||||
##### System Requirements
|
||||
Access to Single-Node GPU to start a vLLM server.
|
||||
:::
|
||||
|
||||
:::{tab-item} tgi
|
||||
##### System Requirements
|
||||
Access to Single-Node GPU to start a TGI server.
|
||||
:::
|
||||
|
||||
:::{tab-item} ollama
|
||||
##### System Requirements
|
||||
Access to Single-Node CPU/GPU able to run ollama.
|
||||
:::
|
||||
|
||||
:::{tab-item} together
|
||||
##### System Requirements
|
||||
Access to Single-Node CPU with Together hosted endpoint via API_KEY from [together.ai](https://api.together.xyz/signin).
|
||||
:::
|
||||
|
||||
:::{tab-item} fireworks
|
||||
##### System Requirements
|
||||
Access to Single-Node CPU with Fireworks hosted endpoint via API_KEY from [fireworks.ai](https://fireworks.ai/).
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
##### 1.1. Start the distribution
|
||||
|
||||
::::{tab-set}
|
||||
:::{tab-item} meta-reference-gpu
|
||||
- [Start Meta Reference GPU Distribution](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/meta-reference-gpu.html)
|
||||
:::
|
||||
|
||||
:::{tab-item} vLLM
|
||||
- [Start vLLM Distribution](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/remote-vllm.html)
|
||||
:::
|
||||
|
||||
:::{tab-item} tgi
|
||||
- [Start TGI Distribution](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/tgi.html)
|
||||
:::
|
||||
|
||||
:::{tab-item} ollama
|
||||
- [Start Ollama Distribution](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/ollama.html)
|
||||
:::
|
||||
|
||||
:::{tab-item} together
|
||||
- [Start Together Distribution](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/together.html)
|
||||
:::
|
||||
|
||||
:::{tab-item} fireworks
|
||||
- [Start Fireworks Distribution](https://llama-stack.readthedocs.io/en/latest/getting_started/distributions/self_hosted_distro/fireworks.html)
|
||||
:::
|
||||
|
||||
::::
|
||||
|
||||
##### Troubleshooting
|
||||
- If you encounter any issues, search through our [GitHub Issues](https://github.com/meta-llama/llama-stack/issues), or file an new issue.
|
||||
- Use `--port <PORT>` flag to use a different port number. For docker run, update the `-p <PORT>:<PORT>` flag.
|
||||
|
||||
|
||||
## Step 2. Run Llama Stack App
|
||||
|
||||
### Chat Completion Test
|
||||
Once the server is set up, we can test it with a client to verify it's working correctly. The following command will send a chat completion request to the server's `/inference/chat_completion` API:
|
||||
### Step 2. Start the Llama Stack server
|
||||
|
||||
```bash
|
||||
$ curl http://localhost:5000/alpha/inference/chat-completion \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model_id": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"messages": [
|
||||
export LLAMA_STACK_PORT=5001
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
llamastack/distribution-ollama \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env OLLAMA_URL=http://host.docker.internal:11434
|
||||
|
||||
```
|
||||
|
||||
### Step 3. Use the Llama Stack client SDK
|
||||
```bash
|
||||
pip install llama-stack-client
|
||||
```
|
||||
|
||||
We will use the `llama-stack-client` CLI to check the connectivity to the server. This should be installed in your environment if you installed the SDK.
|
||||
```bash
|
||||
llama-stack-client --endpoint http://localhost:5001 models list
|
||||
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
|
||||
┃ identifier ┃ provider_id ┃ provider_resource_id ┃ metadata ┃
|
||||
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
|
||||
│ meta-llama/Llama-3.2-3B-Instruct │ ollama │ llama3.2:3b-instruct-fp16 │ {} │
|
||||
└──────────────────────────────────┴─────────────┴───────────────────────────┴──────────┘
|
||||
```
|
||||
|
||||
Chat completion using the CLI
|
||||
```bash
|
||||
llama-stack-client --endpoint http://localhost:5001 inference chat_completion --message "hello, what model are you?"
|
||||
```
|
||||
|
||||
Simple python example using the client SDK
|
||||
```python
|
||||
from llama_stack_client import LlamaStackClient
|
||||
|
||||
client = LlamaStackClient(base_url="http://localhost:5001")
|
||||
|
||||
# List available models
|
||||
models = client.models.list()
|
||||
print(models)
|
||||
|
||||
# Simple chat completion
|
||||
response = client.inference.chat_completion(
|
||||
model_id="meta-llama/Llama-3.2-3B-Instruct",
|
||||
messages=[
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Write me a 2 sentence poem about the moon"}
|
||||
],
|
||||
"sampling_params": {"temperature": 0.7, "seed": 42, "max_tokens": 512}
|
||||
}'
|
||||
|
||||
Output:
|
||||
{'completion_message': {'role': 'assistant',
|
||||
'content': 'The moon glows softly in the midnight sky, \nA beacon of wonder, as it catches the eye.',
|
||||
'stop_reason': 'out_of_tokens',
|
||||
'tool_calls': []},
|
||||
'logprobs': null}
|
||||
|
||||
{"role": "user", "content": "Write a haiku about coding"}
|
||||
]
|
||||
)
|
||||
print(response.completion_message.content)
|
||||
```
|
||||
|
||||
### Run Agent App
|
||||
### Step 4. Your first RAG agent
|
||||
```python
|
||||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
To run an agent app, check out examples demo scripts with client SDKs to talk with the Llama Stack server in our [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repo. To run a simple agent app:
|
||||
import asyncio
|
||||
|
||||
```bash
|
||||
$ git clone git@github.com:meta-llama/llama-stack-apps.git
|
||||
$ cd llama-stack-apps
|
||||
$ pip install -r requirements.txt
|
||||
import fire
|
||||
|
||||
$ python -m examples.agents.client <host> <port>
|
||||
from llama_stack_client import LlamaStackClient
|
||||
from llama_stack_client.lib.agents.agent import Agent
|
||||
from llama_stack_client.lib.agents.event_logger import EventLogger
|
||||
from llama_stack_client.types import Attachment
|
||||
from llama_stack_client.types.agent_create_params import AgentConfig
|
||||
|
||||
|
||||
async def run_main(host: str, port: int, disable_safety: bool = False):
|
||||
urls = [
|
||||
"memory_optimizations.rst",
|
||||
"chat.rst",
|
||||
"llama3.rst",
|
||||
"datasets.rst",
|
||||
"qat_finetune.rst",
|
||||
"lora_finetune.rst",
|
||||
]
|
||||
|
||||
attachments = [
|
||||
Attachment(
|
||||
content=f"https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/{url}",
|
||||
mime_type="text/plain",
|
||||
)
|
||||
for i, url in enumerate(urls)
|
||||
]
|
||||
|
||||
client = LlamaStackClient(
|
||||
base_url=f"http://{host}:{port}",
|
||||
)
|
||||
|
||||
available_shields = [shield.identifier for shield in client.shields.list()]
|
||||
if not available_shields:
|
||||
print("No available shields. Disable safety.")
|
||||
else:
|
||||
print(f"Available shields found: {available_shields}")
|
||||
available_models = [model.identifier for model in client.models.list()]
|
||||
if not available_models:
|
||||
raise ValueError("No available models")
|
||||
else:
|
||||
selected_model = available_models[0]
|
||||
print(f"Using model: {selected_model}")
|
||||
|
||||
agent_config = AgentConfig(
|
||||
model=selected_model,
|
||||
instructions="You are a helpful assistant",
|
||||
sampling_params={
|
||||
"strategy": "greedy",
|
||||
"temperature": 1.0,
|
||||
"top_p": 0.9,
|
||||
},
|
||||
tools=[
|
||||
{
|
||||
"type": "memory",
|
||||
"memory_bank_configs": [],
|
||||
"query_generator_config": {"type": "default", "sep": " "},
|
||||
"max_tokens_in_context": 4096,
|
||||
"max_chunks": 10,
|
||||
},
|
||||
],
|
||||
tool_choice="auto",
|
||||
tool_prompt_format="json",
|
||||
input_shields=available_shields if available_shields else [],
|
||||
output_shields=available_shields if available_shields else [],
|
||||
enable_session_persistence=False,
|
||||
)
|
||||
|
||||
agent = Agent(client, agent_config)
|
||||
session_id = agent.create_session("test-session")
|
||||
print(f"Created session_id={session_id} for Agent({agent.agent_id})")
|
||||
|
||||
user_prompts = [
|
||||
(
|
||||
"I am attaching some documentation for Torchtune. Help me answer questions I will ask next.",
|
||||
attachments,
|
||||
),
|
||||
(
|
||||
"What are the top 5 topics that were explained? Only list succinct bullet points.",
|
||||
None,
|
||||
),
|
||||
(
|
||||
"Was anything related to 'Llama3' discussed, if so what?",
|
||||
None,
|
||||
),
|
||||
(
|
||||
"Tell me how to use LoRA",
|
||||
None,
|
||||
),
|
||||
(
|
||||
"What about Quantization?",
|
||||
None,
|
||||
),
|
||||
]
|
||||
|
||||
for prompt in user_prompts:
|
||||
response = agent.create_turn(
|
||||
messages=[
|
||||
{
|
||||
"role": "user",
|
||||
"content": prompt[0],
|
||||
}
|
||||
],
|
||||
attachments=prompt[1],
|
||||
session_id=session_id,
|
||||
)
|
||||
|
||||
async for log in EventLogger().log(response):
|
||||
log.print()
|
||||
|
||||
|
||||
def main(host: str, port: int):
|
||||
asyncio.run(run_main(host, port))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
fire.Fire(main)
|
||||
```
|
||||
|
||||
You will see outputs of the form --
|
||||
```
|
||||
User> I am planning a trip to Switzerland, what are the top 3 places to visit?
|
||||
inference> Switzerland is a beautiful country with a rich history, stunning landscapes, and vibrant culture. Here are three must-visit places to add to your itinerary:
|
||||
...
|
||||
## Next Steps
|
||||
|
||||
User> What is so special about #1?
|
||||
inference> Jungfraujoch, also known as the "Top of Europe," is a unique and special place for several reasons:
|
||||
...
|
||||
- You can mix and match different providers for inference, memory, agents, evals etc. See [Building custom distributions](../distributions/index.md)
|
||||
- [Developer Cookbook](developer_cookbook.md)
|
||||
|
||||
User> What other countries should I consider to club?
|
||||
inference> Considering your interest in Switzerland, here are some neighboring countries that you may want to consider visiting:
|
||||
```
|
||||
For example applications and more detailed tutorials, visit our [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository.
|
||||
|
|
|
|||
|
|
@ -7,8 +7,7 @@ The Stack APIs are rapidly improving but still a work-in-progress. We invite fee
|
|||
|
||||
```{image} ../_static/llama-stack.png
|
||||
:alt: Llama Stack
|
||||
:width: 600px
|
||||
:align: center
|
||||
:width: 400px
|
||||
```
|
||||
|
||||
## APIs
|
||||
|
|
@ -86,8 +85,10 @@ You can find more example scripts with client SDKs to talk with the Llama Stack
|
|||
:maxdepth: 3
|
||||
|
||||
getting_started/index
|
||||
cli_reference/index
|
||||
cli_reference/download_models
|
||||
distributions/index
|
||||
llama_cli_reference/index
|
||||
llama_cli_reference/download_models
|
||||
llama_stack_client_cli_reference/index
|
||||
api_providers/index
|
||||
distribution_dev/index
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
# CLI Reference
|
||||
# llama CLI Reference
|
||||
|
||||
The `llama` CLI tool helps you setup and use the Llama Stack. It should be available on your path after installing the `llama-stack` package.
|
||||
|
||||
|
|
@ -119,7 +119,7 @@ You should see a table like this:
|
|||
|
||||
To download models, you can use the llama download command.
|
||||
|
||||
#### Downloading from [Meta](https://llama.meta.com/llama-downloads/)
|
||||
### Downloading from [Meta](https://llama.meta.com/llama-downloads/)
|
||||
|
||||
Here is an example download command to get the 3B-Instruct/11B-Vision-Instruct model. You will need META_URL which can be obtained from [here](https://llama.meta.com/docs/getting_the_models/meta/)
|
||||
|
||||
|
|
@ -137,7 +137,7 @@ llama download --source meta --model-id Prompt-Guard-86M --meta-url META_URL
|
|||
llama download --source meta --model-id Llama-Guard-3-1B --meta-url META_URL
|
||||
```
|
||||
|
||||
#### Downloading from [Hugging Face](https://huggingface.co/meta-llama)
|
||||
### Downloading from [Hugging Face](https://huggingface.co/meta-llama)
|
||||
|
||||
Essentially, the same commands above work, just replace `--source meta` with `--source huggingface`.
|
||||
|
||||
162
docs/source/llama_stack_client_cli_reference/index.md
Normal file
162
docs/source/llama_stack_client_cli_reference/index.md
Normal file
|
|
@ -0,0 +1,162 @@
|
|||
# llama-stack-client CLI Reference
|
||||
|
||||
You may use the `llama-stack-client` to query information about the distribution.
|
||||
|
||||
## Basic Commands
|
||||
|
||||
### `llama-stack-client`
|
||||
```bash
|
||||
$ llama-stack-client -h
|
||||
|
||||
usage: llama-stack-client [-h] {models,memory_banks,shields} ...
|
||||
|
||||
Welcome to the LlamaStackClient CLI
|
||||
|
||||
options:
|
||||
-h, --help show this help message and exit
|
||||
|
||||
subcommands:
|
||||
{models,memory_banks,shields}
|
||||
```
|
||||
|
||||
### `llama-stack-client configure`
|
||||
```bash
|
||||
$ llama-stack-client configure
|
||||
> Enter the host name of the Llama Stack distribution server: localhost
|
||||
> Enter the port number of the Llama Stack distribution server: 5000
|
||||
Done! You can now use the Llama Stack Client CLI with endpoint http://localhost:5000
|
||||
```
|
||||
|
||||
## Provider Commands
|
||||
|
||||
### `llama-stack-client providers list`
|
||||
```bash
|
||||
$ llama-stack-client providers list
|
||||
```
|
||||
```
|
||||
+-----------+----------------+-----------------+
|
||||
| API | Provider ID | Provider Type |
|
||||
+===========+================+=================+
|
||||
| scoring | meta0 | meta-reference |
|
||||
+-----------+----------------+-----------------+
|
||||
| datasetio | meta0 | meta-reference |
|
||||
+-----------+----------------+-----------------+
|
||||
| inference | tgi0 | remote::tgi |
|
||||
+-----------+----------------+-----------------+
|
||||
| memory | meta-reference | meta-reference |
|
||||
+-----------+----------------+-----------------+
|
||||
| agents | meta-reference | meta-reference |
|
||||
+-----------+----------------+-----------------+
|
||||
| telemetry | meta-reference | meta-reference |
|
||||
+-----------+----------------+-----------------+
|
||||
| safety | meta-reference | meta-reference |
|
||||
+-----------+----------------+-----------------+
|
||||
```
|
||||
|
||||
## Model Management
|
||||
|
||||
### `llama-stack-client models list`
|
||||
```bash
|
||||
$ llama-stack-client models list
|
||||
```
|
||||
```
|
||||
+----------------------+----------------------+---------------+----------------------------------------------------------+
|
||||
| identifier | llama_model | provider_id | metadata |
|
||||
+======================+======================+===============+==========================================================+
|
||||
| Llama3.1-8B-Instruct | Llama3.1-8B-Instruct | tgi0 | {'huggingface_repo': 'meta-llama/Llama-3.1-8B-Instruct'} |
|
||||
+----------------------+----------------------+---------------+----------------------------------------------------------+
|
||||
```
|
||||
|
||||
### `llama-stack-client models get`
|
||||
```bash
|
||||
$ llama-stack-client models get Llama3.1-8B-Instruct
|
||||
```
|
||||
|
||||
```
|
||||
+----------------------+----------------------+----------------------------------------------------------+---------------+
|
||||
| identifier | llama_model | metadata | provider_id |
|
||||
+======================+======================+==========================================================+===============+
|
||||
| Llama3.1-8B-Instruct | Llama3.1-8B-Instruct | {'huggingface_repo': 'meta-llama/Llama-3.1-8B-Instruct'} | tgi0 |
|
||||
+----------------------+----------------------+----------------------------------------------------------+---------------+
|
||||
```
|
||||
|
||||
|
||||
```bash
|
||||
$ llama-stack-client models get Random-Model
|
||||
|
||||
Model RandomModel is not found at distribution endpoint host:port. Please ensure endpoint is serving specified model.
|
||||
```
|
||||
|
||||
### `llama-stack-client models register`
|
||||
|
||||
```bash
|
||||
$ llama-stack-client models register <model_id> [--provider-id <provider_id>] [--provider-model-id <provider_model_id>] [--metadata <metadata>]
|
||||
```
|
||||
|
||||
### `llama-stack-client models update`
|
||||
|
||||
```bash
|
||||
$ llama-stack-client models update <model_id> [--provider-id <provider_id>] [--provider-model-id <provider_model_id>] [--metadata <metadata>]
|
||||
```
|
||||
|
||||
### `llama-stack-client models delete`
|
||||
|
||||
```bash
|
||||
$ llama-stack-client models delete <model_id>
|
||||
```
|
||||
|
||||
## Memory Bank Management
|
||||
|
||||
### `llama-stack-client memory_banks list`
|
||||
```bash
|
||||
$ llama-stack-client memory_banks list
|
||||
```
|
||||
```
|
||||
+--------------+----------------+--------+-------------------+------------------------+--------------------------+
|
||||
| identifier | provider_id | type | embedding_model | chunk_size_in_tokens | overlap_size_in_tokens |
|
||||
+==============+================+========+===================+========================+==========================+
|
||||
| test_bank | meta-reference | vector | all-MiniLM-L6-v2 | 512 | 64 |
|
||||
+--------------+----------------+--------+-------------------+------------------------+--------------------------+
|
||||
```
|
||||
|
||||
## Shield Management
|
||||
|
||||
### `llama-stack-client shields list`
|
||||
```bash
|
||||
$ llama-stack-client shields list
|
||||
```
|
||||
|
||||
```
|
||||
+--------------+----------+----------------+-------------+
|
||||
| identifier | params | provider_id | type |
|
||||
+==============+==========+================+=============+
|
||||
| llama_guard | {} | meta-reference | llama_guard |
|
||||
+--------------+----------+----------------+-------------+
|
||||
```
|
||||
|
||||
## Evaluation Tasks
|
||||
|
||||
### `llama-stack-client eval_tasks list`
|
||||
```bash
|
||||
$ llama-stack-client eval run_benchmark <task_id1> <task_id2> --num-examples 10 --output-dir ./ --eval-task-config ~/eval_task_config.json
|
||||
```
|
||||
|
||||
where `eval_task_config.json` is the path to the eval task config file in JSON format. An example eval_task_config
|
||||
```
|
||||
$ cat ~/eval_task_config.json
|
||||
{
|
||||
"type": "benchmark",
|
||||
"eval_candidate": {
|
||||
"type": "model",
|
||||
"model": "Llama3.1-405B-Instruct",
|
||||
"sampling_params": {
|
||||
"strategy": "greedy",
|
||||
"temperature": 0,
|
||||
"top_p": 0.95,
|
||||
"top_k": 0,
|
||||
"max_tokens": 0,
|
||||
"repetition_penalty": 1.0
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
|
@ -8,7 +8,6 @@ import argparse
|
|||
|
||||
from llama_stack.cli.subcommand import Subcommand
|
||||
from llama_stack.distribution.datatypes import * # noqa: F403
|
||||
import importlib
|
||||
import os
|
||||
import shutil
|
||||
from functools import lru_cache
|
||||
|
|
@ -258,6 +257,7 @@ class StackBuild(Subcommand):
|
|||
) -> None:
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
|
||||
import yaml
|
||||
from termcolor import cprint
|
||||
|
|
@ -286,17 +286,19 @@ class StackBuild(Subcommand):
|
|||
os.makedirs(build_dir, exist_ok=True)
|
||||
run_config_file = build_dir / f"{build_config.name}-run.yaml"
|
||||
shutil.copy(template_path, run_config_file)
|
||||
module_name = f"llama_stack.templates.{template_name}"
|
||||
module = importlib.import_module(module_name)
|
||||
distribution_template = module.get_distribution_template()
|
||||
|
||||
with open(template_path, "r") as f:
|
||||
yaml_content = f.read()
|
||||
|
||||
# Find all ${env.VARIABLE} patterns
|
||||
env_vars = set(re.findall(r"\${env\.([A-Za-z0-9_]+)}", yaml_content))
|
||||
cprint("Build Successful! Next steps: ", color="green")
|
||||
env_vars = ", ".join(distribution_template.run_config_env_vars.keys())
|
||||
cprint(
|
||||
f" 1. Set the environment variables: {env_vars}",
|
||||
f" 1. Set the environment variables: {list(env_vars)}",
|
||||
color="green",
|
||||
)
|
||||
cprint(
|
||||
f" 2. `llama stack run {run_config_file}`",
|
||||
f" 2. Run: `llama stack run {template_name}`",
|
||||
color="green",
|
||||
)
|
||||
else:
|
||||
|
|
|
|||
|
|
@ -5,9 +5,12 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import argparse
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.cli.subcommand import Subcommand
|
||||
|
||||
REPO_ROOT = Path(__file__).parent.parent.parent.parent
|
||||
|
||||
|
||||
class StackRun(Subcommand):
|
||||
def __init__(self, subparsers: argparse._SubParsersAction):
|
||||
|
|
@ -48,8 +51,6 @@ class StackRun(Subcommand):
|
|||
)
|
||||
|
||||
def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
|
||||
from pathlib import Path
|
||||
|
||||
import pkg_resources
|
||||
import yaml
|
||||
|
||||
|
|
@ -66,19 +67,27 @@ class StackRun(Subcommand):
|
|||
return
|
||||
|
||||
config_file = Path(args.config)
|
||||
if not config_file.exists() and not args.config.endswith(".yaml"):
|
||||
has_yaml_suffix = args.config.endswith(".yaml")
|
||||
|
||||
if not config_file.exists() and not has_yaml_suffix:
|
||||
# check if this is a template
|
||||
config_file = (
|
||||
Path(REPO_ROOT) / "llama_stack" / "templates" / args.config / "run.yaml"
|
||||
)
|
||||
|
||||
if not config_file.exists() and not has_yaml_suffix:
|
||||
# check if it's a build config saved to conda dir
|
||||
config_file = Path(
|
||||
BUILDS_BASE_DIR / ImageType.conda.value / f"{args.config}-run.yaml"
|
||||
)
|
||||
|
||||
if not config_file.exists() and not args.config.endswith(".yaml"):
|
||||
if not config_file.exists() and not has_yaml_suffix:
|
||||
# check if it's a build config saved to docker dir
|
||||
config_file = Path(
|
||||
BUILDS_BASE_DIR / ImageType.docker.value / f"{args.config}-run.yaml"
|
||||
)
|
||||
|
||||
if not config_file.exists() and not args.config.endswith(".yaml"):
|
||||
if not config_file.exists() and not has_yaml_suffix:
|
||||
# check if it's a build config saved to ~/.llama dir
|
||||
config_file = Path(
|
||||
DISTRIBS_BASE_DIR
|
||||
|
|
@ -92,6 +101,7 @@ class StackRun(Subcommand):
|
|||
)
|
||||
return
|
||||
|
||||
print(f"Using config file: {config_file}")
|
||||
config_dict = yaml.safe_load(config_file.read_text())
|
||||
config = parse_and_maybe_upgrade_config(config_dict)
|
||||
|
||||
|
|
|
|||
|
|
@ -122,7 +122,7 @@ add_to_docker <<EOF
|
|||
# This would be good in production but for debugging flexibility lets not add it right now
|
||||
# We need a more solid production ready entrypoint.sh anyway
|
||||
#
|
||||
ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
|
||||
ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server", "--template", "$build_name"]
|
||||
|
||||
EOF
|
||||
|
||||
|
|
|
|||
|
|
@ -170,13 +170,6 @@ class CommonRoutingTableImpl(RoutingTable):
|
|||
# Get existing objects from registry
|
||||
existing_obj = await self.dist_registry.get(obj.type, obj.identifier)
|
||||
|
||||
# Check for existing registration
|
||||
if existing_obj and existing_obj.provider_id == obj.provider_id:
|
||||
print(
|
||||
f"`{obj.identifier}` already registered with `{existing_obj.provider_id}`"
|
||||
)
|
||||
return existing_obj
|
||||
|
||||
# if provider_id is not specified, pick an arbitrary one from existing entries
|
||||
if not obj.provider_id and len(self.impls_by_provider_id) > 0:
|
||||
obj.provider_id = list(self.impls_by_provider_id.keys())[0]
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@ import traceback
|
|||
import warnings
|
||||
|
||||
from contextlib import asynccontextmanager
|
||||
from pathlib import Path
|
||||
from ssl import SSLError
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
|
|
@ -49,6 +50,9 @@ from llama_stack.distribution.stack import (
|
|||
from .endpoints import get_all_api_endpoints
|
||||
|
||||
|
||||
REPO_ROOT = Path(__file__).parent.parent.parent.parent
|
||||
|
||||
|
||||
def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
|
||||
log = file if hasattr(file, "write") else sys.stderr
|
||||
traceback.print_stack(file=log)
|
||||
|
|
@ -279,9 +283,12 @@ def main():
|
|||
parser = argparse.ArgumentParser(description="Start the LlamaStack server.")
|
||||
parser.add_argument(
|
||||
"--yaml-config",
|
||||
default="llamastack-run.yaml",
|
||||
help="Path to YAML configuration file",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--template",
|
||||
help="One of the template names in llama_stack/templates (e.g., tgi, fireworks, remote-vllm, etc.)",
|
||||
)
|
||||
parser.add_argument("--port", type=int, default=5000, help="Port to listen on")
|
||||
parser.add_argument(
|
||||
"--disable-ipv6", action="store_true", help="Whether to disable IPv6 support"
|
||||
|
|
@ -303,10 +310,29 @@ def main():
|
|||
print(f"Error: {str(e)}")
|
||||
sys.exit(1)
|
||||
|
||||
with open(args.yaml_config, "r") as fp:
|
||||
if args.yaml_config:
|
||||
# if the user provided a config file, use it, even if template was specified
|
||||
config_file = Path(args.yaml_config)
|
||||
if not config_file.exists():
|
||||
raise ValueError(f"Config file {config_file} does not exist")
|
||||
print(f"Using config file: {config_file}")
|
||||
elif args.template:
|
||||
config_file = (
|
||||
Path(REPO_ROOT) / "llama_stack" / "templates" / args.template / "run.yaml"
|
||||
)
|
||||
if not config_file.exists():
|
||||
raise ValueError(f"Template {args.template} does not exist")
|
||||
print(f"Using template {args.template} config file: {config_file}")
|
||||
else:
|
||||
raise ValueError("Either --yaml-config or --template must be provided")
|
||||
|
||||
with open(config_file, "r") as fp:
|
||||
config = replace_env_vars(yaml.safe_load(fp))
|
||||
config = StackRunConfig(**config)
|
||||
|
||||
print("Run configuration:")
|
||||
print(yaml.dump(config.model_dump(), indent=2))
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
try:
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from typing import Optional
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from llama_models.datatypes import * # noqa: F403
|
||||
from llama_models.sku_list import resolve_model
|
||||
|
|
@ -37,8 +37,10 @@ class MetaReferenceInferenceConfig(BaseModel):
|
|||
@classmethod
|
||||
def validate_model(cls, model: str) -> str:
|
||||
permitted_models = supported_inference_models()
|
||||
if model not in permitted_models:
|
||||
model_list = "\n\t".join(permitted_models)
|
||||
descriptors = [m.descriptor() for m in permitted_models]
|
||||
repos = [m.huggingface_repo for m in permitted_models]
|
||||
if model not in (descriptors + repos):
|
||||
model_list = "\n\t".join(repos)
|
||||
raise ValueError(
|
||||
f"Unknown model: `{model}`. Choose from [\n\t{model_list}\n]"
|
||||
)
|
||||
|
|
@ -54,6 +56,7 @@ class MetaReferenceInferenceConfig(BaseModel):
|
|||
cls,
|
||||
model: str = "Llama3.2-3B-Instruct",
|
||||
checkpoint_dir: str = "${env.CHECKPOINT_DIR:null}",
|
||||
**kwargs,
|
||||
) -> Dict[str, Any]:
|
||||
return {
|
||||
"model": model,
|
||||
|
|
@ -64,3 +67,16 @@ class MetaReferenceInferenceConfig(BaseModel):
|
|||
|
||||
class MetaReferenceQuantizedInferenceConfig(MetaReferenceInferenceConfig):
|
||||
quantization: QuantizationConfig
|
||||
|
||||
@classmethod
|
||||
def sample_run_config(
|
||||
cls,
|
||||
model: str = "Llama3.2-3B-Instruct",
|
||||
checkpoint_dir: str = "${env.CHECKPOINT_DIR:null}",
|
||||
**kwargs,
|
||||
) -> Dict[str, Any]:
|
||||
config = super().sample_run_config(model, checkpoint_dir, **kwargs)
|
||||
config["quantization"] = {
|
||||
"type": "fp8",
|
||||
}
|
||||
return config
|
||||
|
|
|
|||
|
|
@ -37,19 +37,22 @@ class VLLMConfig(BaseModel):
|
|||
@classmethod
|
||||
def sample_run_config(cls):
|
||||
return {
|
||||
"model": "${env.VLLM_INFERENCE_MODEL:Llama3.2-3B-Instruct}",
|
||||
"tensor_parallel_size": "${env.VLLM_TENSOR_PARALLEL_SIZE:1}",
|
||||
"max_tokens": "${env.VLLM_MAX_TOKENS:4096}",
|
||||
"enforce_eager": "${env.VLLM_ENFORCE_EAGER:False}",
|
||||
"gpu_memory_utilization": "${env.VLLM_GPU_MEMORY_UTILIZATION:0.3}",
|
||||
"model": "${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}",
|
||||
"tensor_parallel_size": "${env.TENSOR_PARALLEL_SIZE:1}",
|
||||
"max_tokens": "${env.MAX_TOKENS:4096}",
|
||||
"enforce_eager": "${env.ENFORCE_EAGER:False}",
|
||||
"gpu_memory_utilization": "${env.GPU_MEMORY_UTILIZATION:0.7}",
|
||||
}
|
||||
|
||||
@field_validator("model")
|
||||
@classmethod
|
||||
def validate_model(cls, model: str) -> str:
|
||||
permitted_models = supported_inference_models()
|
||||
if model not in permitted_models:
|
||||
model_list = "\n\t".join(permitted_models)
|
||||
|
||||
descriptors = [m.descriptor() for m in permitted_models]
|
||||
repos = [m.huggingface_repo for m in permitted_models]
|
||||
if model not in (descriptors + repos):
|
||||
model_list = "\n\t".join(repos)
|
||||
raise ValueError(
|
||||
f"Unknown model: `{model}`. Choose from [\n\t{model_list}\n]"
|
||||
)
|
||||
|
|
|
|||
|
|
@ -4,11 +4,8 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_models.schema_utils import json_schema_type
|
||||
|
||||
from llama_stack.providers.utils.bedrock.config import BedrockBaseConfig
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class BedrockConfig(BedrockBaseConfig):
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -37,6 +37,18 @@ class InferenceEndpointImplConfig(BaseModel):
|
|||
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def sample_run_config(
|
||||
cls,
|
||||
endpoint_name: str = "${env.INFERENCE_ENDPOINT_NAME}",
|
||||
api_token: str = "${env.HF_API_TOKEN}",
|
||||
**kwargs,
|
||||
):
|
||||
return {
|
||||
"endpoint_name": endpoint_name,
|
||||
"api_token": api_token,
|
||||
}
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class InferenceAPIImplConfig(BaseModel):
|
||||
|
|
@ -47,3 +59,15 @@ class InferenceAPIImplConfig(BaseModel):
|
|||
default=None,
|
||||
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def sample_run_config(
|
||||
cls,
|
||||
repo: str = "${env.INFERENCE_MODEL}",
|
||||
api_token: str = "${env.HF_API_TOKEN}",
|
||||
**kwargs,
|
||||
):
|
||||
return {
|
||||
"huggingface_repo": repo,
|
||||
"api_token": api_token,
|
||||
}
|
||||
|
|
|
|||
|
|
@ -147,9 +147,7 @@ class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
|
|||
documents: List[MemoryBankDocument],
|
||||
ttl_seconds: Optional[int] = None,
|
||||
) -> None:
|
||||
index = self.cache.get(bank_id, None)
|
||||
if not index:
|
||||
raise ValueError(f"Bank {bank_id} not found")
|
||||
index = await self._get_and_cache_bank_index(bank_id)
|
||||
|
||||
await index.insert_documents(documents)
|
||||
|
||||
|
|
@ -159,8 +157,20 @@ class ChromaMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
|
|||
query: InterleavedTextMedia,
|
||||
params: Optional[Dict[str, Any]] = None,
|
||||
) -> QueryDocumentsResponse:
|
||||
index = self.cache.get(bank_id, None)
|
||||
if not index:
|
||||
raise ValueError(f"Bank {bank_id} not found")
|
||||
index = await self._get_and_cache_bank_index(bank_id)
|
||||
|
||||
return await index.query_documents(query, params)
|
||||
|
||||
async def _get_and_cache_bank_index(self, bank_id: str) -> BankWithIndex:
|
||||
if bank_id in self.cache:
|
||||
return self.cache[bank_id]
|
||||
|
||||
bank = await self.memory_bank_store.get_memory_bank(bank_id)
|
||||
if not bank:
|
||||
raise ValueError(f"Bank {bank_id} not found in Llama Stack")
|
||||
collection = await self.client.get_collection(bank_id)
|
||||
if not collection:
|
||||
raise ValueError(f"Bank {bank_id} not found in Chroma")
|
||||
index = BankWithIndex(bank=bank, index=ChromaIndex(self.client, collection))
|
||||
self.cache[bank_id] = index
|
||||
return index
|
||||
|
|
|
|||
|
|
@ -201,10 +201,7 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
|
|||
documents: List[MemoryBankDocument],
|
||||
ttl_seconds: Optional[int] = None,
|
||||
) -> None:
|
||||
index = self.cache.get(bank_id, None)
|
||||
if not index:
|
||||
raise ValueError(f"Bank {bank_id} not found")
|
||||
|
||||
index = await self._get_and_cache_bank_index(bank_id)
|
||||
await index.insert_documents(documents)
|
||||
|
||||
async def query_documents(
|
||||
|
|
@ -213,8 +210,17 @@ class PGVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
|
|||
query: InterleavedTextMedia,
|
||||
params: Optional[Dict[str, Any]] = None,
|
||||
) -> QueryDocumentsResponse:
|
||||
index = self.cache.get(bank_id, None)
|
||||
if not index:
|
||||
raise ValueError(f"Bank {bank_id} not found")
|
||||
|
||||
index = await self._get_and_cache_bank_index(bank_id)
|
||||
return await index.query_documents(query, params)
|
||||
|
||||
async def _get_and_cache_bank_index(self, bank_id: str) -> BankWithIndex:
|
||||
if bank_id in self.cache:
|
||||
return self.cache[bank_id]
|
||||
|
||||
bank = await self.memory_bank_store.get_memory_bank(bank_id)
|
||||
index = BankWithIndex(
|
||||
bank=bank,
|
||||
index=PGVectorIndex(bank, ALL_MINILM_L6_V2_DIMENSION, self.cursor),
|
||||
)
|
||||
self.cache[bank_id] = index
|
||||
return index
|
||||
|
|
|
|||
|
|
@ -11,7 +11,6 @@ import pytest
|
|||
#
|
||||
# pytest -v -s llama_stack/providers/tests/inference/test_model_registration.py
|
||||
# -m "meta_reference"
|
||||
# --env TOGETHER_API_KEY=<your_api_key>
|
||||
|
||||
|
||||
class TestModelRegistration:
|
||||
|
|
|
|||
|
|
@ -5,11 +5,9 @@
|
|||
# the root directory of this source tree.
|
||||
from typing import Optional
|
||||
|
||||
from llama_models.schema_utils import json_schema_type
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
@json_schema_type
|
||||
class BedrockBaseConfig(BaseModel):
|
||||
aws_access_key_id: Optional[str] = Field(
|
||||
default=None,
|
||||
|
|
@ -57,3 +55,7 @@ class BedrockBaseConfig(BaseModel):
|
|||
default=3600,
|
||||
description="The time in seconds till a session expires. The default is 3600 seconds (1 hour).",
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def sample_run_config(cls, **kwargs):
|
||||
return {}
|
||||
|
|
|
|||
|
|
@ -22,9 +22,9 @@ def is_supported_safety_model(model: Model) -> bool:
|
|||
]
|
||||
|
||||
|
||||
def supported_inference_models() -> List[str]:
|
||||
def supported_inference_models() -> List[Model]:
|
||||
return [
|
||||
m.descriptor()
|
||||
m
|
||||
for m in all_registered_models()
|
||||
if (
|
||||
m.model_family in {ModelFamily.llama3_1, ModelFamily.llama3_2}
|
||||
|
|
|
|||
|
|
@ -178,7 +178,9 @@ def chat_completion_request_to_messages(
|
|||
cprint(f"Could not resolve model {llama_model}", color="red")
|
||||
return request.messages
|
||||
|
||||
if model.descriptor() not in supported_inference_models():
|
||||
allowed_models = supported_inference_models()
|
||||
descriptors = [m.descriptor() for m in allowed_models]
|
||||
if model.descriptor() not in descriptors:
|
||||
cprint(f"Unsupported inference model? {model.descriptor()}", color="red")
|
||||
return request.messages
|
||||
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ def process_template(template_dir: Path, progress) -> None:
|
|||
template.save_distribution(
|
||||
yaml_output_dir=REPO_ROOT / "llama_stack" / "templates" / template.name,
|
||||
doc_output_dir=REPO_ROOT
|
||||
/ "docs/source/getting_started/distributions"
|
||||
/ "docs/source/distributions"
|
||||
/ f"{template.distro_type}_distro",
|
||||
)
|
||||
else:
|
||||
|
|
@ -103,7 +103,7 @@ def generate_dependencies_file():
|
|||
|
||||
deps_file = REPO_ROOT / "distributions" / "dependencies.json"
|
||||
with open(deps_file, "w") as f:
|
||||
json.dump(distribution_deps, f, indent=2)
|
||||
f.write(json.dumps(distribution_deps, indent=2) + "\n")
|
||||
|
||||
|
||||
def main():
|
||||
|
|
|
|||
7
llama_stack/templates/bedrock/__init__.py
Normal file
7
llama_stack/templates/bedrock/__init__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from .bedrock import get_distribution_template # noqa: F401
|
||||
38
llama_stack/templates/bedrock/bedrock.py
Normal file
38
llama_stack/templates/bedrock/bedrock.py
Normal file
|
|
@ -0,0 +1,38 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::bedrock"],
|
||||
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["remote::bedrock"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
}
|
||||
|
||||
return DistributionTemplate(
|
||||
name="bedrock",
|
||||
distro_type="self_hosted",
|
||||
description="Use AWS Bedrock for running LLM inference and safety",
|
||||
docker_image=None,
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
default_models=[],
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMASTACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
},
|
||||
)
|
||||
|
|
@ -1,9 +1,19 @@
|
|||
version: '2'
|
||||
name: bedrock
|
||||
distribution_spec:
|
||||
description: Use Amazon Bedrock APIs.
|
||||
description: Use AWS Bedrock for running LLM inference and safety
|
||||
docker_image: null
|
||||
providers:
|
||||
inference: remote::bedrock
|
||||
memory: inline::faiss
|
||||
safety: inline::llama-guard
|
||||
agents: inline::meta-reference
|
||||
telemetry: inline::meta-reference
|
||||
inference:
|
||||
- remote::bedrock
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety:
|
||||
- remote::bedrock
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
image_type: conda
|
||||
|
|
|
|||
70
llama_stack/templates/bedrock/doc_template.md
Normal file
70
llama_stack/templates/bedrock/doc_template.md
Normal file
|
|
@ -0,0 +1,70 @@
|
|||
# Bedrock Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
|
||||
|
||||
{{ providers_table }}
|
||||
|
||||
|
||||
{% 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 %}
|
||||
|
||||
{% if default_models %}
|
||||
### Models
|
||||
|
||||
The following models are available by default:
|
||||
|
||||
{% for model in default_models %}
|
||||
- `{{ model.model_id }} ({{ model.provider_model_id }})`
|
||||
{% endfor %}
|
||||
{% endif %}
|
||||
|
||||
|
||||
### Prerequisite: API Keys
|
||||
|
||||
Make sure you have access to a AWS Bedrock API Key. You can get one by visiting [AWS Bedrock](https://aws.amazon.com/bedrock/).
|
||||
|
||||
|
||||
## Running Llama Stack with AWS Bedrock
|
||||
|
||||
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.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=5001
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
|
||||
--env AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
|
||||
--env AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
```bash
|
||||
llama stack build --template {{ name }} --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
|
||||
--env AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
|
||||
--env AWS_SESSION_TOKEN=$AWS_SESSION_TOKEN
|
||||
```
|
||||
49
llama_stack/templates/bedrock/run.yaml
Normal file
49
llama_stack/templates/bedrock/run.yaml
Normal file
|
|
@ -0,0 +1,49 @@
|
|||
version: '2'
|
||||
image_name: bedrock
|
||||
docker_image: null
|
||||
conda_env: bedrock
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: bedrock
|
||||
provider_type: remote::bedrock
|
||||
config: {}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: bedrock
|
||||
provider_type: remote::bedrock
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/bedrock}/registry.db
|
||||
models: []
|
||||
shields: []
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
|
|
@ -1,9 +0,0 @@
|
|||
name: databricks
|
||||
distribution_spec:
|
||||
description: Use Databricks for running LLM inference
|
||||
providers:
|
||||
inference: remote::databricks
|
||||
memory: inline::faiss
|
||||
safety: inline::llama-guard
|
||||
agents: meta-reference
|
||||
telemetry: meta-reference
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Fireworks Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
|
||||
|
||||
{{ providers_table }}
|
||||
|
|
@ -43,9 +50,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
|
||||
```
|
||||
|
|
@ -55,6 +60,6 @@ docker run \
|
|||
```bash
|
||||
llama stack build --template fireworks --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port 5001 \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env FIREWORKS_API_KEY=$FIREWORKS_API_KEY
|
||||
```
|
||||
|
|
|
|||
7
llama_stack/templates/hf-endpoint/__init__.py
Normal file
7
llama_stack/templates/hf-endpoint/__init__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from .hf_endpoint import get_distribution_template # noqa: F401
|
||||
|
|
@ -1,9 +1,19 @@
|
|||
version: '2'
|
||||
name: hf-endpoint
|
||||
distribution_spec:
|
||||
description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
|
||||
description: Use (an external) Hugging Face Inference Endpoint for running LLM inference
|
||||
docker_image: null
|
||||
providers:
|
||||
inference: remote::hf::endpoint
|
||||
memory: inline::faiss
|
||||
safety: inline::llama-guard
|
||||
agents: inline::meta-reference
|
||||
telemetry: inline::meta-reference
|
||||
inference:
|
||||
- remote::hf::endpoint
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
image_type: conda
|
||||
|
|
|
|||
97
llama_stack/templates/hf-endpoint/hf_endpoint.py
Normal file
97
llama_stack/templates/hf-endpoint/hf_endpoint.py
Normal file
|
|
@ -0,0 +1,97 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
|
||||
from llama_stack.providers.remote.inference.tgi import InferenceEndpointImplConfig
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::hf::endpoint"],
|
||||
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
}
|
||||
|
||||
inference_provider = Provider(
|
||||
provider_id="hf-endpoint",
|
||||
provider_type="remote::hf::endpoint",
|
||||
config=InferenceEndpointImplConfig.sample_run_config(),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="hf-endpoint",
|
||||
)
|
||||
safety_model = ModelInput(
|
||||
model_id="${env.SAFETY_MODEL}",
|
||||
provider_id="hf-endpoint-safety",
|
||||
)
|
||||
|
||||
return DistributionTemplate(
|
||||
name="hf-endpoint",
|
||||
distro_type="self_hosted",
|
||||
description="Use (an external) Hugging Face Inference Endpoint for running LLM inference",
|
||||
docker_image=None,
|
||||
template_path=None,
|
||||
providers=providers,
|
||||
default_models=[inference_model, safety_model],
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider],
|
||||
},
|
||||
default_models=[inference_model],
|
||||
),
|
||||
"run-with-safety.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [
|
||||
inference_provider,
|
||||
Provider(
|
||||
provider_id="hf-endpoint-safety",
|
||||
provider_type="remote::hf::endpoint",
|
||||
config=InferenceEndpointImplConfig.sample_run_config(
|
||||
endpoint_name="${env.SAFETY_INFERENCE_ENDPOINT_NAME}",
|
||||
),
|
||||
),
|
||||
]
|
||||
},
|
||||
default_models=[
|
||||
inference_model,
|
||||
safety_model,
|
||||
],
|
||||
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMASTACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"HF_API_TOKEN": (
|
||||
"hf_...",
|
||||
"Hugging Face API token",
|
||||
),
|
||||
"INFERENCE_ENDPOINT_NAME": (
|
||||
"",
|
||||
"HF Inference endpoint name for the main inference model",
|
||||
),
|
||||
"SAFETY_INFERENCE_ENDPOINT_NAME": (
|
||||
"",
|
||||
"HF Inference endpoint for the safety model",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model served by the HF Inference Endpoint",
|
||||
),
|
||||
"SAFETY_MODEL": (
|
||||
"meta-llama/Llama-Guard-3-1B",
|
||||
"Safety model served by the HF Inference Endpoint",
|
||||
),
|
||||
},
|
||||
)
|
||||
68
llama_stack/templates/hf-endpoint/run-with-safety.yaml
Normal file
68
llama_stack/templates/hf-endpoint/run-with-safety.yaml
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
version: '2'
|
||||
image_name: hf-endpoint
|
||||
docker_image: null
|
||||
conda_env: hf-endpoint
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: hf-endpoint
|
||||
provider_type: remote::hf::endpoint
|
||||
config:
|
||||
endpoint_name: ${env.INFERENCE_ENDPOINT_NAME}
|
||||
api_token: ${env.HF_API_TOKEN}
|
||||
- provider_id: hf-endpoint-safety
|
||||
provider_type: remote::hf::endpoint
|
||||
config:
|
||||
endpoint_name: ${env.SAFETY_INFERENCE_ENDPOINT_NAME}
|
||||
api_token: ${env.HF_API_TOKEN}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: hf-endpoint
|
||||
provider_model_id: null
|
||||
- metadata: {}
|
||||
model_id: ${env.SAFETY_MODEL}
|
||||
provider_id: hf-endpoint-safety
|
||||
provider_model_id: null
|
||||
shields:
|
||||
- params: null
|
||||
shield_id: ${env.SAFETY_MODEL}
|
||||
provider_id: null
|
||||
provider_shield_id: null
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
55
llama_stack/templates/hf-endpoint/run.yaml
Normal file
55
llama_stack/templates/hf-endpoint/run.yaml
Normal file
|
|
@ -0,0 +1,55 @@
|
|||
version: '2'
|
||||
image_name: hf-endpoint
|
||||
docker_image: null
|
||||
conda_env: hf-endpoint
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: hf-endpoint
|
||||
provider_type: remote::hf::endpoint
|
||||
config:
|
||||
endpoint_name: ${env.INFERENCE_ENDPOINT_NAME}
|
||||
api_token: ${env.HF_API_TOKEN}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-endpoint}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: hf-endpoint
|
||||
provider_model_id: null
|
||||
shields: []
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
7
llama_stack/templates/hf-serverless/__init__.py
Normal file
7
llama_stack/templates/hf-serverless/__init__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from .hf_serverless import get_distribution_template # noqa: F401
|
||||
|
|
@ -1,9 +1,19 @@
|
|||
version: '2'
|
||||
name: hf-serverless
|
||||
distribution_spec:
|
||||
description: "Like local, but use Hugging Face Inference API (serverless) for running LLM inference.\nSee https://hf.co/docs/api-inference."
|
||||
description: Use (an external) Hugging Face Inference Endpoint for running LLM inference
|
||||
docker_image: null
|
||||
providers:
|
||||
inference: remote::hf::serverless
|
||||
memory: inline::faiss
|
||||
safety: inline::llama-guard
|
||||
agents: inline::meta-reference
|
||||
telemetry: inline::meta-reference
|
||||
inference:
|
||||
- remote::hf::serverless
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
image_type: conda
|
||||
|
|
|
|||
89
llama_stack/templates/hf-serverless/hf_serverless.py
Normal file
89
llama_stack/templates/hf-serverless/hf_serverless.py
Normal file
|
|
@ -0,0 +1,89 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
|
||||
from llama_stack.providers.remote.inference.tgi import InferenceAPIImplConfig
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::hf::serverless"],
|
||||
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
}
|
||||
|
||||
inference_provider = Provider(
|
||||
provider_id="hf-serverless",
|
||||
provider_type="remote::hf::serverless",
|
||||
config=InferenceAPIImplConfig.sample_run_config(),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="hf-serverless",
|
||||
)
|
||||
safety_model = ModelInput(
|
||||
model_id="${env.SAFETY_MODEL}",
|
||||
provider_id="hf-serverless-safety",
|
||||
)
|
||||
|
||||
return DistributionTemplate(
|
||||
name="hf-serverless",
|
||||
distro_type="self_hosted",
|
||||
description="Use (an external) Hugging Face Inference Endpoint for running LLM inference",
|
||||
docker_image=None,
|
||||
template_path=None,
|
||||
providers=providers,
|
||||
default_models=[inference_model, safety_model],
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider],
|
||||
},
|
||||
default_models=[inference_model],
|
||||
),
|
||||
"run-with-safety.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [
|
||||
inference_provider,
|
||||
Provider(
|
||||
provider_id="hf-serverless-safety",
|
||||
provider_type="remote::hf::serverless",
|
||||
config=InferenceAPIImplConfig.sample_run_config(
|
||||
repo="${env.SAFETY_MODEL}",
|
||||
),
|
||||
),
|
||||
]
|
||||
},
|
||||
default_models=[
|
||||
inference_model,
|
||||
safety_model,
|
||||
],
|
||||
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMASTACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"HF_API_TOKEN": (
|
||||
"hf_...",
|
||||
"Hugging Face API token",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model to be served by the HF Serverless endpoint",
|
||||
),
|
||||
"SAFETY_MODEL": (
|
||||
"meta-llama/Llama-Guard-3-1B",
|
||||
"Safety model to be served by the HF Serverless endpoint",
|
||||
),
|
||||
},
|
||||
)
|
||||
68
llama_stack/templates/hf-serverless/run-with-safety.yaml
Normal file
68
llama_stack/templates/hf-serverless/run-with-safety.yaml
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
version: '2'
|
||||
image_name: hf-serverless
|
||||
docker_image: null
|
||||
conda_env: hf-serverless
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: hf-serverless
|
||||
provider_type: remote::hf::serverless
|
||||
config:
|
||||
huggingface_repo: ${env.INFERENCE_MODEL}
|
||||
api_token: ${env.HF_API_TOKEN}
|
||||
- provider_id: hf-serverless-safety
|
||||
provider_type: remote::hf::serverless
|
||||
config:
|
||||
huggingface_repo: ${env.SAFETY_MODEL}
|
||||
api_token: ${env.HF_API_TOKEN}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: hf-serverless
|
||||
provider_model_id: null
|
||||
- metadata: {}
|
||||
model_id: ${env.SAFETY_MODEL}
|
||||
provider_id: hf-serverless-safety
|
||||
provider_model_id: null
|
||||
shields:
|
||||
- params: null
|
||||
shield_id: ${env.SAFETY_MODEL}
|
||||
provider_id: null
|
||||
provider_shield_id: null
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
55
llama_stack/templates/hf-serverless/run.yaml
Normal file
55
llama_stack/templates/hf-serverless/run.yaml
Normal file
|
|
@ -0,0 +1,55 @@
|
|||
version: '2'
|
||||
image_name: hf-serverless
|
||||
docker_image: null
|
||||
conda_env: hf-serverless
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: hf-serverless
|
||||
provider_type: remote::hf::serverless
|
||||
config:
|
||||
huggingface_repo: ${env.INFERENCE_MODEL}
|
||||
api_token: ${env.HF_API_TOKEN}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/hf-serverless}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: hf-serverless
|
||||
provider_model_id: null
|
||||
shields: []
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
|
|
@ -1,13 +0,0 @@
|
|||
name: meta-reference-gpu
|
||||
distribution_spec:
|
||||
docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
|
||||
description: Use code from `llama_stack` itself to serve all llama stack APIs
|
||||
providers:
|
||||
inference: inline::meta-reference
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety: inline::llama-guard
|
||||
agents: inline::meta-reference
|
||||
telemetry: inline::meta-reference
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Meta Reference Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
|
||||
|
||||
{{ providers_table }}
|
||||
|
|
@ -40,9 +47,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
/root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
|
@ -53,9 +58,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run-with-safety.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
/root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
|
|
@ -66,8 +69,8 @@ docker run \
|
|||
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
|
||||
|
||||
```bash
|
||||
llama stack build --template meta-reference-gpu --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
llama stack build --template {{ name }} --image-type conda
|
||||
llama stack run distributions/{{ name }}/run.yaml \
|
||||
--port 5001 \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
|
@ -75,7 +78,7 @@ llama stack run ./run.yaml \
|
|||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run ./run-with-safety.yaml \
|
||||
llama stack run distributions/{{ name }}/run-with-safety.yaml \
|
||||
--port 5001 \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
|
|
|
|||
|
|
@ -0,0 +1,7 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from .meta_reference import get_distribution_template # noqa: F401
|
||||
|
|
@ -1,13 +1,19 @@
|
|||
version: '2'
|
||||
name: meta-reference-quantized-gpu
|
||||
distribution_spec:
|
||||
docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
|
||||
description: Use code from `llama_stack` itself to serve all llama stack APIs
|
||||
description: Use Meta Reference with fp8, int4 quantization for running LLM inference
|
||||
docker_image: null
|
||||
providers:
|
||||
inference: meta-reference-quantized
|
||||
inference:
|
||||
- inline::meta-reference-quantized
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety: inline::llama-guard
|
||||
agents: inline::meta-reference
|
||||
telemetry: inline::meta-reference
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
image_type: conda
|
||||
|
|
|
|||
|
|
@ -0,0 +1,87 @@
|
|||
# Meta Reference Quantized Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
|
||||
|
||||
{{ providers_table }}
|
||||
|
||||
The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc.
|
||||
|
||||
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 make sure you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/cli_reference/download_models.html) here to download the models. Run `llama model list` to see the available models to download, and `llama model download` to download the checkpoints.
|
||||
|
||||
```
|
||||
$ ls ~/.llama/checkpoints
|
||||
Llama3.1-8B Llama3.2-11B-Vision-Instruct Llama3.2-1B-Instruct Llama3.2-90B-Vision-Instruct Llama-Guard-3-8B
|
||||
Llama3.1-8B-Instruct Llama3.2-1B Llama3.2-3B-Instruct Llama-Guard-3-1B Prompt-Guard-86M
|
||||
```
|
||||
|
||||
## Running the Distribution
|
||||
|
||||
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.
|
||||
|
||||
```bash
|
||||
LLAMA_STACK_PORT=5001
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
|
||||
|
||||
```bash
|
||||
llama stack build --template {{ name }} --image-type conda
|
||||
llama stack run distributions/{{ name }}/run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run distributions/{{ name }}/run-with-safety.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
|
||||
--env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
|
||||
```
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.distribution.datatypes import ModelInput, Provider
|
||||
from llama_stack.providers.inline.inference.meta_reference import (
|
||||
MetaReferenceQuantizedInferenceConfig,
|
||||
)
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["inline::meta-reference-quantized"],
|
||||
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
}
|
||||
|
||||
inference_provider = Provider(
|
||||
provider_id="meta-reference-inference",
|
||||
provider_type="inline::meta-reference-quantized",
|
||||
config=MetaReferenceQuantizedInferenceConfig.sample_run_config(
|
||||
model="${env.INFERENCE_MODEL}",
|
||||
checkpoint_dir="${env.INFERENCE_CHECKPOINT_DIR:null}",
|
||||
),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="meta-reference-inference",
|
||||
)
|
||||
return DistributionTemplate(
|
||||
name="meta-reference-quantized-gpu",
|
||||
distro_type="self_hosted",
|
||||
description="Use Meta Reference with fp8, int4 quantization for running LLM inference",
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
default_models=[inference_model],
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider],
|
||||
},
|
||||
default_models=[inference_model],
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMASTACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model loaded into the Meta Reference server",
|
||||
),
|
||||
"INFERENCE_CHECKPOINT_DIR": (
|
||||
"null",
|
||||
"Directory containing the Meta Reference model checkpoint",
|
||||
),
|
||||
},
|
||||
)
|
||||
58
llama_stack/templates/meta-reference-quantized-gpu/run.yaml
Normal file
58
llama_stack/templates/meta-reference-quantized-gpu/run.yaml
Normal file
|
|
@ -0,0 +1,58 @@
|
|||
version: '2'
|
||||
image_name: meta-reference-quantized-gpu
|
||||
docker_image: null
|
||||
conda_env: meta-reference-quantized-gpu
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: meta-reference-inference
|
||||
provider_type: inline::meta-reference-quantized
|
||||
config:
|
||||
model: ${env.INFERENCE_MODEL}
|
||||
max_seq_len: 4096
|
||||
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
|
||||
quantization:
|
||||
type: fp8
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: meta-reference-inference
|
||||
provider_model_id: null
|
||||
shields: []
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
|
|
@ -1,5 +1,12 @@
|
|||
# Ollama Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
|
||||
|
||||
{{ providers_table }}
|
||||
|
|
@ -55,9 +62,7 @@ docker run \
|
|||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ~/.llama:/root/.llama \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env OLLAMA_URL=http://host.docker.internal:11434
|
||||
|
|
@ -86,7 +91,7 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
|
|||
```bash
|
||||
export LLAMA_STACK_PORT=5001
|
||||
|
||||
llama stack build --template ollama --image-type conda
|
||||
llama stack build --template {{ name }} --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
|
|
|
|||
|
|
@ -1,4 +1,10 @@
|
|||
# Remote vLLM Distribution
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
|||
|
||||
class RunConfigSettings(BaseModel):
|
||||
provider_overrides: Dict[str, List[Provider]] = Field(default_factory=dict)
|
||||
default_models: List[ModelInput]
|
||||
default_models: Optional[List[ModelInput]] = None
|
||||
default_shields: Optional[List[ShieldInput]] = None
|
||||
|
||||
def run_config(
|
||||
|
|
@ -87,7 +87,7 @@ class RunConfigSettings(BaseModel):
|
|||
__distro_dir__=f"distributions/{name}",
|
||||
db_name="registry.db",
|
||||
),
|
||||
models=self.default_models,
|
||||
models=self.default_models or [],
|
||||
shields=self.default_shields or [],
|
||||
)
|
||||
|
||||
|
|
@ -104,7 +104,7 @@ class DistributionTemplate(BaseModel):
|
|||
|
||||
providers: Dict[str, List[str]]
|
||||
run_configs: Dict[str, RunConfigSettings]
|
||||
template_path: Path
|
||||
template_path: Optional[Path] = None
|
||||
|
||||
# Optional configuration
|
||||
run_config_env_vars: Optional[Dict[str, Tuple[str, str]]] = None
|
||||
|
|
@ -159,6 +159,7 @@ class DistributionTemplate(BaseModel):
|
|||
with open(yaml_output_dir / yaml_pth, "w") as f:
|
||||
yaml.safe_dump(run_config.model_dump(), f, sort_keys=False)
|
||||
|
||||
docs = self.generate_markdown_docs()
|
||||
with open(doc_output_dir / f"{self.name}.md", "w") as f:
|
||||
f.write(docs)
|
||||
if self.template_path:
|
||||
docs = self.generate_markdown_docs()
|
||||
with open(doc_output_dir / f"{self.name}.md", "w") as f:
|
||||
f.write(docs if docs.endswith("\n") else docs + "\n")
|
||||
|
|
|
|||
|
|
@ -1,5 +1,12 @@
|
|||
# TGI Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
|
||||
|
||||
{{ providers_table }}
|
||||
|
|
@ -71,9 +78,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env TGI_URL=http://host.docker.internal:$INFERENCE_PORT
|
||||
|
|
@ -102,18 +107,18 @@ Make sure you have done `pip install llama-stack` and have the Llama Stack CLI a
|
|||
```bash
|
||||
llama stack build --template {{ name }} --image-type conda
|
||||
llama stack run ./run.yaml
|
||||
--port 5001
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT
|
||||
```
|
||||
|
||||
If you are using Llama Stack Safety / Shield APIs, use:
|
||||
|
||||
```bash
|
||||
llama stack run ./run-with-safety.yaml
|
||||
--port 5001
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL
|
||||
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT
|
||||
--env SAFETY_MODEL=$SAFETY_MODEL
|
||||
llama stack run ./run-with-safety.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env INFERENCE_MODEL=$INFERENCE_MODEL \
|
||||
--env TGI_URL=http://127.0.0.1:$INFERENCE_PORT \
|
||||
--env SAFETY_MODEL=$SAFETY_MODEL \
|
||||
--env TGI_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,4 +1,11 @@
|
|||
# Fireworks Distribution
|
||||
# Together Distribution
|
||||
|
||||
```{toctree}
|
||||
:maxdepth: 2
|
||||
:hidden:
|
||||
|
||||
self
|
||||
```
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
|
||||
|
||||
|
|
@ -43,9 +50,7 @@ LLAMA_STACK_PORT=5001
|
|||
docker run \
|
||||
-it \
|
||||
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
|
||||
-v ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--yaml-config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env TOGETHER_API_KEY=$TOGETHER_API_KEY
|
||||
```
|
||||
|
|
@ -53,8 +58,8 @@ docker run \
|
|||
### Via Conda
|
||||
|
||||
```bash
|
||||
llama stack build --template together --image-type conda
|
||||
llama stack build --template {{ name }} --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port 5001 \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env TOGETHER_API_KEY=$TOGETHER_API_KEY
|
||||
```
|
||||
|
|
|
|||
7
llama_stack/templates/vllm-gpu/__init__.py
Normal file
7
llama_stack/templates/vllm-gpu/__init__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from .vllm import get_distribution_template # noqa: F401
|
||||
19
llama_stack/templates/vllm-gpu/build.yaml
Normal file
19
llama_stack/templates/vllm-gpu/build.yaml
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
version: '2'
|
||||
name: vllm-gpu
|
||||
distribution_spec:
|
||||
description: Use a built-in vLLM engine for running LLM inference
|
||||
docker_image: null
|
||||
providers:
|
||||
inference:
|
||||
- inline::vllm
|
||||
memory:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
image_type: conda
|
||||
58
llama_stack/templates/vllm-gpu/run.yaml
Normal file
58
llama_stack/templates/vllm-gpu/run.yaml
Normal file
|
|
@ -0,0 +1,58 @@
|
|||
version: '2'
|
||||
image_name: vllm-gpu
|
||||
docker_image: null
|
||||
conda_env: vllm-gpu
|
||||
apis:
|
||||
- agents
|
||||
- inference
|
||||
- memory
|
||||
- safety
|
||||
- telemetry
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: vllm
|
||||
provider_type: inline::vllm
|
||||
config:
|
||||
model: ${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}
|
||||
tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:1}
|
||||
max_tokens: ${env.MAX_TOKENS:4096}
|
||||
enforce_eager: ${env.ENFORCE_EAGER:False}
|
||||
gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.7}
|
||||
memory:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config: {}
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config: {}
|
||||
metadata_store:
|
||||
namespace: null
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: vllm
|
||||
provider_model_id: null
|
||||
shields: []
|
||||
memory_banks: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
eval_tasks: []
|
||||
74
llama_stack/templates/vllm-gpu/vllm.py
Normal file
74
llama_stack/templates/vllm-gpu/vllm.py
Normal file
|
|
@ -0,0 +1,74 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.distribution.datatypes import ModelInput, Provider
|
||||
from llama_stack.providers.inline.inference.vllm import VLLMConfig
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["inline::vllm"],
|
||||
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
}
|
||||
|
||||
inference_provider = Provider(
|
||||
provider_id="vllm",
|
||||
provider_type="inline::vllm",
|
||||
config=VLLMConfig.sample_run_config(),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="vllm",
|
||||
)
|
||||
|
||||
return DistributionTemplate(
|
||||
name="vllm-gpu",
|
||||
distro_type="self_hosted",
|
||||
description="Use a built-in vLLM engine for running LLM inference",
|
||||
docker_image=None,
|
||||
template_path=None,
|
||||
providers=providers,
|
||||
default_models=[inference_model],
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider],
|
||||
},
|
||||
default_models=[inference_model],
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMASTACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model loaded into the vLLM engine",
|
||||
),
|
||||
"TENSOR_PARALLEL_SIZE": (
|
||||
"1",
|
||||
"Number of tensor parallel replicas (number of GPUs to use).",
|
||||
),
|
||||
"MAX_TOKENS": (
|
||||
"4096",
|
||||
"Maximum number of tokens to generate.",
|
||||
),
|
||||
"ENFORCE_EAGER": (
|
||||
"False",
|
||||
"Whether to use eager mode for inference (otherwise cuda graphs are used).",
|
||||
),
|
||||
"GPU_MEMORY_UTILIZATION": (
|
||||
"0.7",
|
||||
"GPU memory utilization for the vLLM engine.",
|
||||
),
|
||||
},
|
||||
)
|
||||
|
|
@ -1,13 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5af4f44e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/00_Inference101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c1e7571c",
|
||||
|
|
@ -1,13 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "785bd3ff",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/01_Local_Cloud_Inference101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a0ed972d",
|
||||
|
|
@ -1,13 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d2bf5275",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/02_Prompt_Engineering101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cd96f85a",
|
||||
|
|
@ -1,13 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6323a6be",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/03_Image_Chat101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "923343b0-d4bd-4361-b8d4-dd29f86a0fbd",
|
||||
|
|
@ -1,12 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/04_Tool_Calling101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -1,12 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/05_Memory101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -1,12 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/06_Safety101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -18,7 +11,7 @@
|
|||
"As outlined in our [Responsible Use Guide](https://www.llama.com/docs/how-to-guides/responsible-use-guide-resources/), LLM apps should deploy appropriate system level safeguards to mitigate safety and security risks of LLM system, similar to the following diagram:\n",
|
||||
"\n",
|
||||
"<div>\n",
|
||||
"<img src=\"../_static/safety_system.webp\" alt=\"Figure 1: Safety System\" width=\"1000\"/>\n",
|
||||
"<img src=\"/docs/_static/safety_system.webp\" alt=\"Figure 1: Safety System\" width=\"1000\"/>\n",
|
||||
"</div>\n",
|
||||
"To that goal, Llama Stack uses **Prompt Guard** and **Llama Guard 3** to secure our system. Here are the quick introduction about them.\n"
|
||||
]
|
||||
|
|
@ -1,12 +1,5 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/zero_to_hero_guide/07_Agents101.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
Loading…
Add table
Add a link
Reference in a new issue