AMD-SHARK-Studio

mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-04-03 03:00:17 -04:00

Files

Stanley Winata 136021424c [SD] Change default VMA large heap block size for windows perf. (#715 )

Windows perform can boost from 2.67s/image to 2.4523s/image.
While Linux stays the same.

2022-12-24 01:40:58 +07:00

2022-12-24 01:40:58 +07:00

index.py

2022-12-23 23:18:27 +05:30

README.md

2022-11-02 20:52:34 +05:30

shark_sd.spec

2022-12-21 19:23:54 -08:00

In order to launch SHARK-web, from the root SHARK directory, run:

Linux

IMPORTER=1 ./setup_venv.sh
source shark.venv/bin/activate
cd web
python index.py

./setup_venv.ps1
cd web
python index.py --local_tank_cache=<current_working_dir>