mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00

Composable building blocks to build Llama Apps https://llama-stack.readthedocs.io

Find a file

Ashwin Bharambe 23014ea4d1 Add hacks because Cloudfront config limits on the 405b model files		2024-07-30 13:46:47 -07:00
docs	model template --template -> model template --name	2024-07-29 18:21:05 -07:00
llama_toolchain	Add hacks because Cloudfront config limits on the 405b model files	2024-07-30 13:46:47 -07:00
.flake8	Initial commit	2024-07-23 08:32:33 -07:00
.gitignore	Initial commit	2024-07-23 08:32:33 -07:00
.pre-commit-config.yaml	Initial commit	2024-07-23 08:32:33 -07:00
CODE_OF_CONDUCT.md	Initial commit	2024-07-23 08:32:33 -07:00
CONTRIBUTING.md	Initial commit	2024-07-23 08:32:33 -07:00
fp8_requirements.txt	Update fp8_requirements, we don't need nightly torch anymore	2024-07-26 08:25:44 -07:00
LICENSE	Initial commit	2024-07-23 08:32:33 -07:00
MANIFEST.in	add requirements to MANIFEST.in	2024-07-23 12:59:28 -07:00
pyproject.toml	Initial commit	2024-07-23 08:32:33 -07:00
README.md	Add links to shields	2024-07-27 11:28:46 -04:00
requirements.txt	Canonical package name for the dependency	2024-07-23 13:30:33 -07:00
setup.py	Bump version to 0.0.2	2024-07-29 23:56:41 -07:00

README.md

llama-toolchain

This repo contains the API specifications for various components of the Llama Stack as well implementations for some of those APIs like model inference.

The Llama Stack consists of toolchain-apis and agentic-apis. This repo contains the toolchain-apis.

Installation

You can install this repository as a package with pip install llama-toolchain

If you want to install from source:

mkdir -p ~/local
cd ~/local
git clone git@github.com:meta-llama/llama-toolchain.git

conda create -n toolchain python=3.10
conda activate toolchain

cd llama-toolchain
pip install -e .

The Llama CLI

The llama CLI makes it easy to configure and run the Llama toolchain. Read the CLI reference 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...)

ENV=fp8_env
conda create -n $ENV python=3.10
conda activate $ENV

pip3 install -r fp8_requirements.txt