appatalks

appatalks/Synapse

Run MoE open weight models, faster - on local hardware.

1 stars 0 forks 1 watchers Python MIT License

cuda heterogeneous-computing inference-engine moe

1 Open Issue Need Help Last updated: Oct 19, 2026

Open Issues Need Help

View All on GitHub

[Feature] AMD ROCm support 15 days ago

help wanted

appatalks/Synapse

1

Run MoE open weight models, faster - on local hardware.

Python

#cuda#heterogeneous-computing#inference-engine#moe