Introduce Llama stack distributions (#22)

* Add distribution CLI scaffolding

* More progress towards `llama distribution install`

* getting closer to a distro definition, distro install + configure works

* Distribution server now functioning

* read existing configuration, save enums properly

* Remove inference uvicorn server entrypoint and llama inference CLI command

* updated dependency and client model name

* Improved exception handling

* local imports for faster cli

* undo a typo, add a passthrough distribution

* implement full-passthrough in the server

* add safety adapters, configuration handling, server + clients

* cleanup, moving stuff to common, nuke utils

* Add a Path() wrapper at the earliest place

* fixes

* Bring agentic system api to toolchain

Add adapter dependencies and resolve adapters using a topological sort

* refactor to reduce size of `agentic_system`

* move straggler files and fix some important existing bugs

* ApiSurface -> Api

* refactor a method out

* Adapter -> Provider

* Make each inference provider into its own subdirectory

* installation fixes

* Rename Distribution -> DistributionSpec, simplify RemoteProviders

* dict key instead of attr

* update inference config to take model and not model_dir

* Fix passthrough streaming, send headers properly not part of body :facepalm

* update safety to use model sku ids and not model dirs

* Update cli_reference.md

* minor fixes

* add DistributionConfig, fix a bug in model download

* Make install + start scripts do proper configuration automatically

* Update CLI_reference

* Nuke fp8_requirements, fold fbgemm into common requirements

* Update README, add newline between API surface configurations

* Refactor download functionality out of the Command so can be reused

* Add `llama model download` alias for `llama download`

* Show message about checksum file so users can check themselves

* Simpler intro statements

* get ollama working

* Reduce a bunch of dependencies from toolchain

Some improvements to the distribution install script

* Avoid using `conda run` since it buffers everything

* update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes

* add validation for configuration input

* resort imports

* make optional subclasses default to yes for configuration

* Remove additional_pip_packages; move deps to providers

* for inline make 8b model the default

* Add scripts to MANIFEST

* allow installing from test.pypi.org

* Fix #2 to help with testing packages

* Must install llama-models at that same version first

* fix PIP_ARGS

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Hardik Shah <hjshah@meta.com>

README.md

@@ -3,9 +3,42 @@
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/llama-toolchain)](https://pypi.org/project/llama-toolchain/)
 [![Discord](https://img.shields.io/discord/1257833999603335178)](https://discord.gg/TZAAYNVtrU)
 
-This repo contains the API specifications for various components of the Llama Stack as well implementations for some of those APIs like model inference.
+This repository contains the specifications and implementations of the APIs which are part of the Llama Stack.
+
+The [Llama Stack](https://github.com/meta-llama/llama-toolchain/pull/8) defines and standardizes the building blocks needed to bring generative AI applications to market. These blocks span the entire development lifecycle: from model training and fine-tuning, through product evaluation, to invoking AI agents in production. Beyond definition, we're developing open-source versions and partnering with cloud providers, ensuring developers can assemble AI solutions using consistent, interlocking pieces across platforms. The ultimate goal is to accelerate innovation in the AI space.
+
+The Stack APIs are rapidly improving, but still very much Work in Progress and we invite feedback as well as direct contributions.
+
+
+## APIs
+
+The Llama Stack consists of the following set of APIs:
+
+- Inference
+- Safety
+- Memory
+- Agentic System
+- Evaluation
+- Post Training
+- Synthetic Data Generation
+- Reward Scoring
+
+Each of the APIs themselves is a collection of REST endpoints.
+
+
+## API Providers
+
+A Provider is what makes the API real -- they provide the actual implementation backing the API.
+
+As an example, for Inference, we could have the implementation be backed by primitives from `[ torch | vLLM | TensorRT ]` as possible options.
+
+A provider can also be just a pointer to a remote REST service -- for example, cloud providers like `[ aws | gcp ]` could possibly serve these APIs.
+
+
+## Llama Stack Distribution
+
+A Distribution is where APIs and Providers are assembled together to provide a consistent whole to the end application developer. You can mix-and-match providers -- some could be backed by inline code and some could be remote. As a hobbyist, you can serve a small model locally, but can choose a cloud provider for a large model. Regardless, the higher level APIs your app needs to work with don't need to change at all. You can even imagine moving across the server / mobile-device boundary as well always using the same uniform set of APIs for developing Generative AI applications.
 
-The Llama Stack consists of toolchain-apis and agentic-apis. This repo contains the toolchain-apis.
 
 ## Installation
 
@@ -27,16 +60,4 @@ pip install -e .
 
 ## The Llama CLI
 
-The `llama` CLI makes it easy to configure and run the Llama toolchain. Read the [CLI reference](docs/cli_reference.md) for details.
-
-## Appendix: Running FP8
-
-If you want to run FP8, you need the `fbgemm-gpu` package which requires `torch >= 2.4.0` (currently only in nightly, but releasing shortly...)
-
-```bash
-ENV=fp8_env
-conda create -n $ENV python=3.10
-conda activate $ENV
-
-pip3 install -r fp8_requirements.txt
-```
+The `llama` CLI makes it easy to work with the Llama Stack set of tools, including installing and running Distributions, downloading models, studying model prompt formats, etc. Please see the [CLI reference](docs/cli_reference.md) for details.