skygpu
/
skynet
mirror of https://github.com/skygpu/skynet.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
skynet/README.md

104 lines
1.9 KiB
Markdown
Raw Normal View History

Started making roboust testing fixtures to init fresh db and skynet Add simple dgpu worker connection test Make db connection handler manage schema and table init logic Keep tweaking dgpu main handler attemtping to fix subactor hangs Change frontend open rpc logic to return a wrapped rpc_call fn referencing the new socket Decupled user config request validation from telegram module Fix next_worker logic, now takes in account multiple tasks per dgpu Add dgpu_workers and dgpu_next calls Fixed readme, moved db init code into db module
2022-12-11 14:02:55 +00:00
# skynet
Add logo to readme
2023-10-09 11:42:09 +00:00
<div align="center">
<img src="https://explorer.skygpu.net/v2/explore/assets/logo.png" width=512 height=512>
</div>
Started making roboust testing fixtures to init fresh db and skynet Add simple dgpu worker connection test Make db connection handler manage schema and table init logic Keep tweaking dgpu main handler attemtping to fix subactor hangs Change frontend open rpc logic to return a wrapped rpc_call fn referencing the new socket Decupled user config request validation from telegram module Fix next_worker logic, now takes in account multiple tasks per dgpu Add dgpu_workers and dgpu_next calls Fixed readme, moved db init code into db module
2022-12-11 14:02:55 +00:00
### decentralized compute platform
Update README.md
2023-05-30 03:41:32 +00:00
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
### native install
system dependencies:
- `cuda` 11.8
- `llvm` 10
- `python` 3.10+
- `docker` (for ipfs node)
Update README.md
2023-05-30 03:41:32 +00:00
```
# create and edit config from template
Switch config to toml
2023-10-06 13:24:44 +00:00
cp skynet.toml.example skynet.toml
Update README.md
2023-05-30 03:41:32 +00:00
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
# install poetry package manager
curl -sSL https://install.python-poetry.org | python3 -
Update README.md
2023-05-30 03:41:32 +00:00
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
# install
poetry install
Update README.md
2023-05-30 03:41:32 +00:00
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
# enable environment
poetry shell
Update README.md
2023-05-30 03:41:32 +00:00
# test you can run this command
skynet --help
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
# launch ipfs node
skynet run ipfs
Update README.md
2023-05-30 03:41:32 +00:00
# to launch worker
skynet run dgpu
```
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
### dockerized install
Add frontend container & run instructions
2023-10-09 10:39:23 +00:00
## frontend
system dependencies:
- `docker`
```
# create and edit config from template
cp skynet.toml.example skynet.toml
# pull runtime container
docker pull guilledk/skynet:runtime-frontend
# run telegram bot
docker run \
-it \
--rm \
--network host \
--name skynet-telegram \
--mount type=bind,source="$(pwd)",target=/root/target \
guilledk/skynet:runtime-frontend \
skynet run telegram --db-pass PASSWORD --db-user USER --db-host HOST
```
## worker
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
system dependencies:
- `docker` with gpu enabled
```
Switch config to toml
2023-10-06 13:24:44 +00:00
# create and edit config from template
cp skynet.toml.example skynet.toml
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
# pull runtime container
docker pull guilledk/skynet:runtime-cuda
# or build it (takes a bit of time)
./build_docker.sh
# launch simple ipfs node
./launch_ipfs.sh
Switch config to toml
2023-10-06 13:24:44 +00:00
# run worker with all gpus
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
docker run \
-it \
--rm \
--gpus all \
--network host \
Add --name to docker worker launch command
2023-10-03 18:42:07 +00:00
--name skynet-worker \
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
--mount type=bind,source="$(pwd)",target=/root/target \
Dont reference python version on docker instructions
2023-10-07 14:04:57 +00:00
guilledk/skynet:runtime-cuda \
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
skynet run dgpu
Switch config to toml
2023-10-06 13:24:44 +00:00
# run worker with specific gpu
docker run \
-it \
--rm \
--gpus '"device=1"' \
--network host \
--name skynet-worker-1 \
--mount type=bind,source="$(pwd)",target=/root/target \
Dont reference python version on docker instructions
2023-10-07 14:04:57 +00:00
guilledk/skynet:runtime-cuda \
Switch config to toml
2023-10-06 13:24:44 +00:00
skynet run dgpu
Add venv to dockerignore Improve readme Improve dockerization as ipfs cli exec runs not needed anymore Fix pyproject toml for gpu workers Add more sections on example config Drop and siomplify many cli commands, try to use config.ini for everything now Use more dynamic imports on cli to speed up startup Improve model pipelines to allow low mem cards to run big models Add upscaler download to `skynet download` cmd
2023-10-03 15:55:57 +00:00
```