# What does this PR do? This PR adds back the changes in #1300 which were reverted in #1476 . It also adds logic to preserve context variables across asyncio boundary. this is needed with the library client since the async generator logic yields control to code outside the event loop, and on resuming, does not have the same context as before and this requires preserving the context vars. address #1477 ## Test Plan ``` curl --request POST \ --url http://localhost:8321/v1/inference/chat-completion \ --header 'content-type: application/json' \ --data '{ "model_id": "meta-llama/Llama-3.1-70B-Instruct", "messages": [ { "role": "user", "content": { "type": "text", "text": "where do humans live" } } ], "stream": false }' | jq . { "metrics": [ { "trace_id": "kCZwO3tyQC-FuAGb", "span_id": "bsP_5a5O", "timestamp": "2025-03-11T16:47:38.549084Z", "attributes": { "model_id": "meta-llama/Llama-3.1-70B-Instruct", "provider_id": "fireworks" }, "type": "metric", "metric": "prompt_tokens", "value": 10, "unit": "tokens" }, { "trace_id": "kCZwO3tyQC-FuAGb", "span_id": "bsP_5a5O", "timestamp": "2025-03-11T16:47:38.549449Z", "attributes": { "model_id": "meta-llama/Llama-3.1-70B-Instruct", "provider_id": "fireworks" }, "type": "metric", "metric": "completion_tokens", "value": 369, "unit": "tokens" }, { "trace_id": "kCZwO3tyQC-FuAGb", "span_id": "bsP_5a5O", "timestamp": "2025-03-11T16:47:38.549457Z", "attributes": { "model_id": "meta-llama/Llama-3.1-70B-Instruct", "provider_id": "fireworks" }, "type": "metric", "metric": "total_tokens", "value": 379, "unit": "tokens" } ], "completion_message": { "role": "assistant", "content": "Humans live on the planet Earth, specifically on its landmasses and in its oceans. Here's a breakdown of where humans live:\n\n1. **Continents:** Humans inhabit all seven continents:\n\t* Africa\n\t* Antarctica ( temporary residents, mostly scientists and researchers)\n\t* Asia\n\t* Australia\n\t* Europe\n\t* North America\n\t* South America\n2. **Countries:** There are 196 countries recognized by the United Nations, and humans live in almost all of them.\n3. **Cities and towns:** Many humans live in urban areas, such as cities and towns, which are often located near coastlines, rivers, or other bodies of water.\n4. **Rural areas:** Some humans live in rural areas, such as villages, farms, and countryside.\n5. **Islands:** Humans inhabit many islands around the world, including those in the Pacific, Indian, and Atlantic Oceans.\n6. **Mountains and highlands:** Humans live in mountainous regions, such as the Himalayas, the Andes, and the Rocky Mountains.\n7. **Deserts:** Some humans live in desert regions, such as the Sahara, the Mojave, and the Atacama.\n8. **Coastal areas:** Many humans live in coastal areas, such as beaches, ports, and coastal cities.\n9. **Underwater habitats:** A few humans live in underwater habitats, such as research stations and submarines.\n10. **Space:** A small number of humans have lived in space, including astronauts on the International Space Station and those who have visited the Moon.\n\nOverall, humans can be found living in almost every environment on Earth, from the frozen tundra to the hottest deserts, and from the highest mountains to the deepest oceans.", "stop_reason": "end_of_turn", "tool_calls": [] }, "logprobs": null } ``` Orignal repro no longer showing any error: ``` LLAMA_STACK_DISABLE_VERSION_CHECK=true llama stack run ~/.llama/distributions/fireworks/fireworks-run.yaml python -m examples.agents.e2e_loop_with_client_tools localhost 8321 ``` client logs: https://gist.github.com/dineshyv/047c7e87b18a5792aa660e311ea53166 server logs: https://gist.github.com/dineshyv/97a2174099619e9916c7c490be26e559 |
||
---|---|---|
.cursor/rules | ||
.github | ||
distributions | ||
docs | ||
llama_stack | ||
rfcs | ||
scripts | ||
tests | ||
.gitignore | ||
.pre-commit-config.yaml | ||
.python-version | ||
.readthedocs.yaml | ||
CHANGELOG.md | ||
CODE_OF_CONDUCT.md | ||
CONTRIBUTING.md | ||
LICENSE | ||
MANIFEST.in | ||
pyproject.toml | ||
README.md | ||
requirements.txt | ||
SECURITY.md | ||
uv.lock |
Llama Stack
Quick Start | Documentation | Colab Notebook
Llama Stack standardizes the core building blocks that simplify AI application development. It codifies best practices across the Llama ecosystem. More specifically, it provides
- Unified API layer for Inference, RAG, Agents, Tools, Safety, Evals, and Telemetry.
- Plugin architecture to support the rich ecosystem of different API implementations in various environments, including local development, on-premises, cloud, and mobile.
- Prepackaged verified distributions which offer a one-stop solution for developers to get started quickly and reliably in any environment.
- Multiple developer interfaces like CLI and SDKs for Python, Typescript, iOS, and Android.
- Standalone applications as examples for how to build production-grade AI applications with Llama Stack.
Llama Stack Benefits
- Flexible Options: Developers can choose their preferred infrastructure without changing APIs and enjoy flexible deployment choices.
- Consistent Experience: With its unified APIs, Llama Stack makes it easier to build, test, and deploy AI applications with consistent application behavior.
- Robust Ecosystem: Llama Stack is already integrated with distribution partners (cloud providers, hardware vendors, and AI-focused companies) that offer tailored infrastructure, software, and services for deploying Llama models.
By reducing friction and complexity, Llama Stack empowers developers to focus on what they do best: building transformative generative AI applications.
API Providers
Here is a list of the various API providers and available distributions that can help developers get started easily with Llama Stack.
API Provider Builder | Environments | Agents | Inference | Memory | Safety | Telemetry |
---|---|---|---|---|---|---|
Meta Reference | Single Node | ✅ | ✅ | ✅ | ✅ | ✅ |
SambaNova | Hosted | ✅ | ||||
Cerebras | Hosted | ✅ | ||||
Fireworks | Hosted | ✅ | ✅ | ✅ | ||
AWS Bedrock | Hosted | ✅ | ✅ | |||
Together | Hosted | ✅ | ✅ | ✅ | ||
Groq | Hosted | ✅ | ||||
Ollama | Single Node | ✅ | ||||
TGI | Hosted and Single Node | ✅ | ||||
NVIDIA NIM | Hosted and Single Node | ✅ | ||||
Chroma | Single Node | ✅ | ||||
PG Vector | Single Node | ✅ | ||||
PyTorch ExecuTorch | On-device iOS | ✅ | ✅ | |||
vLLM | Hosted and Single Node | ✅ |
Distributions
A Llama Stack Distribution (or "distro") is a pre-configured bundle of provider implementations for each API component. Distributions make it easy to get started with a specific deployment scenario - you can begin with a local development setup (eg. ollama) and seamlessly transition to production (eg. Fireworks) without changing your application code. Here are some of the distributions we support:
Distribution | Llama Stack Docker | Start This Distribution |
---|---|---|
Meta Reference | llamastack/distribution-meta-reference-gpu | Guide |
Meta Reference Quantized | llamastack/distribution-meta-reference-quantized-gpu | Guide |
SambaNova | llamastack/distribution-sambanova | Guide |
Cerebras | llamastack/distribution-cerebras | Guide |
Ollama | llamastack/distribution-ollama | Guide |
TGI | llamastack/distribution-tgi | Guide |
Together | llamastack/distribution-together | Guide |
Fireworks | llamastack/distribution-fireworks | Guide |
vLLM | llamastack/distribution-remote-vllm | Guide |
Installation
You have two ways to install this repository:
-
Install as a package: You can install the repository directly from PyPI by running the following command:
pip install llama-stack
-
Install from source: If you prefer to install from the source code, we recommend using uv. Then, run the following commands:
git clone git@github.com:meta-llama/llama-stack.git cd llama-stack uv sync uv pip install -e .
Documentation
Please checkout our Documentation page for more details.
- CLI references
- llama (server-side) CLI Reference: Guide for using the
llama
CLI to work with Llama models (download, study prompts), and building/starting a Llama Stack distribution. - llama (client-side) CLI Reference: Guide for using the
llama-stack-client
CLI, which allows you to query information about the distribution.
- llama (server-side) CLI Reference: Guide for using the
- Getting Started
- Quick guide to start a Llama Stack server.
- Jupyter notebook to walk-through how to use simple text and vision inference llama_stack_client APIs
- The complete Llama Stack lesson Colab notebook of the new Llama 3.2 course on Deeplearning.ai.
- A Zero-to-Hero Guide that guide you through all the key components of llama stack with code samples.
- Contributing
- Adding a new API Provider to walk-through how to add a new API provider.
Llama Stack Client SDKs
Language | Client SDK | Package |
---|---|---|
Python | llama-stack-client-python | |
Swift | llama-stack-client-swift | |
Typescript | llama-stack-client-typescript | |
Kotlin | llama-stack-client-kotlin |
Check out our client SDKs for connecting to a Llama Stack server in your preferred language, you can choose from python, typescript, swift, and kotlin programming languages to quickly build your applications.
You can find more example scripts with client SDKs to talk with the Llama Stack server in our llama-stack-apps repo.