dragonpilot

mirror of https://github.com/dragonpilot/dragonpilot.git synced 2026-02-20 17:13:54 +08:00

Files

Adeeb Shihadeh 4ded4c53af thneed: printf -> cloudlog (#31506 )

* thneed: printf -> cloudlog

* LOGI

* Revert "LOGI"

This reverts commit e6ab7e45fb7f3678727595f67c1f6c8e2cda734b.

2024-02-18 23:04:24 -08:00

__init__.py

model: mse err from 0.02-> 0.000056 (#23891 )

2022-03-02 20:52:17 -08:00

README

thneed saves 45% of a core (#1512 )

2020-05-15 13:53:01 -07:00

serialize.cc

thneed: printf -> cloudlog (#31506 )

2024-02-18 23:04:24 -08:00

thneed_common.cc

Rocket Launcher Model (#25963 )

2022-10-05 21:43:38 -07:00

thneed_pc.cc

modeld: delete unused SNPE stuff after move to tinygrad (#25635 )

2022-09-01 18:28:20 -07:00

thneed_qcom2.cc

Disable error message in thneed ioctl interceptor to fix pyenv issues

2023-08-24 14:41:04 -07:00

thneed.h

Revert "Switch from json11 to nlohmann/json (#31093 )"

2024-01-22 22:41:59 -08:00

README

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.