StarPilot

mirror of https://github.com/firestar5683/StarPilot.git synced 2026-07-08 07:02:06 +08:00

Files

T

Dean Lee db211ce617 cpplint: add filter whitespace/parens (#29565 )

old-commit-hash: 5480d32bb5d98d57100fd709b9ffe7bfcc6e020a

2023-08-23 14:25:05 -07:00

__init__.py

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

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

lib.py

CI: Pylint to ruff (#29294 )

2023-08-09 13:26:54 -07:00

README

thneed saves 45% of a core (#1512 )

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

serialize.cc

cpplint: add filter whitespace/parens (#29565 )

2023-08-23 14:25:05 -07:00

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

thneed: cleanup duplicate GPU config (#28487 )

2023-06-11 13:26:41 -07:00

thneed.h

move all third party stuff into third_party/ (#26853 )

2022-12-31 21:00:50 -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.