Skip to content

Latest commit

 

History

History
57 lines (40 loc) · 976 Bytes

dev.md

File metadata and controls

57 lines (40 loc) · 976 Bytes

Env setup

Make sure you have a local GPU to run vllm with, for now.

1. Mac

1.0 Env
pyenv local 3.12.4
poetry env use $(pyenv which python)
poetry install --with dev --no-root
poetry shell

2. Linux

2.0 Bootstrap

sudo -E bash dev/bootstrap.sh

2.1 Install deps

poetry env use 3.12
poetry install --no-root
poetry shell

Run stuff

1. Create the network

docker network create chutes

2. Start all the things

2.0 Base components

docker compose up -d

2.1 [Optional, requires GPU] run the "miner" (dummy vllm instance)

docker compose -f docker-compose-gpu.yml up -d vllm

2.2 [Optional, requires GPU] run the "graval" node validator

docker compose -f docker-compose-gpu.yml up -d graval

If you do NOT want to verify GPUs/don't have GPU locally, be sure to set the SKIP_GPU_VERIFICATION env variable to true in the api service.