mirror of
https://github.com/dragonpilot/dragonpilot.git
synced 2026-02-25 15:03:53 +08:00
0fc4b4df98
* improve the thneed compiler * only init thneed if we are using the GPU Co-authored-by: Comma Device <device@comma.ai>
thneed is an SNPE accelerator. I know SNPE is already an accelerator, but sometimes things need to go even faster.. It runs on the local device, and caches a single model run. Then it replays it, but fast. thneed slices through abstraction layers like a fish. You need a thneed.