Decentralized compute layer
 
 
Go to file
Guillermo Rodriguez 82458bb4c8
Merge pull request #23 from guilledk/full_http_ipfs
Async IPFS apis, drop docker on worker & other nice sprites ☠
2023-10-03 13:00:45 -03:00
docker Remove old docker stuff and upgrade telegram frontend to use ipfs async apis 2023-09-28 21:23:04 -03:00
skynet Add new ipfs options to cli frontend 2023-09-28 21:43:30 -03:00
tests Add test for new ipfs async apis, fix cli entrypoints endpoint loading to new format 2023-09-24 15:23:25 -03:00
.dockerignore Rework dgpu client to be single task 2022-12-17 11:39:42 -03:00
.gitignore Snappier dgpu, fix captioning & gitignores 2023-05-29 19:03:39 -03:00
LICENSE Update LICENSE 2023-04-09 19:50:08 -03:00
README.md Update README.md 2023-05-30 00:41:32 -03:00
build_docker.sh Use leap as network + auth layer, we decentarlized now 2023-05-22 06:10:51 -03:00
pytest.ini Add test for new ipfs async apis, fix cli entrypoints endpoint loading to new format 2023-09-24 15:23:25 -03:00
requirements.cuda.0.txt change stable2 model and how stablexl loads, add reqs 2023-07-19 17:25:28 -04:00
requirements.cuda.1.txt First decupled architecture, still working on integrating tractor gpu workers 2022-12-10 18:18:03 -03:00
requirements.cuda.2.txt Separate cuda build in a third step 2023-01-16 00:26:04 -03:00
requirements.txt initial discord bot 2023-07-17 01:18:08 -04:00
setup.py Add img2img mode 2023-01-15 23:42:45 -03:00
skynet.ini.example Add new ipfs options to cli frontend 2023-09-28 21:43:30 -03:00

README.md

skynet

decentralized compute platform

To launch a worker:

# create and edit config from template
cp skynet.ini.example skynet.ini

# create python virtual envoirment 3.10+
python3 -m venv venv

# enable envoirment
source venv/bin/activate

# install requirements
pip install -r requirements.txt
pip install -r requirements.cuda.0.txt
pip install -r requirements.cuda.1.txt
pip install -r requirements.cuda.2.txt

# install skynet
pip install -e .

# test you can run this command
skynet --help

# to launch worker
skynet run dgpu