mawei/StarPilot
1
0
Fork 0
mirror of https://github.com/firestar5683/StarPilot.git synced 2026-07-01 03:22:07 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
1edd9bfb60cc1d99fa838aba02f19acf6936d23e
StarPilot/selfdrive/modeld/thneed
T
History
Comma Device 123fd2f6ee thneed: a few asserts in the optimizer for cases it will fail 
old-commit-hash: 2b652605a08178e539d7ff7ab7e009b4da29bd46
2022-02-21 12:08:52 -08:00
..
include
thneed saves 45% of a core (#1512)
2020-05-15 13:53:01 -07:00
kernels
Refactor convolutions (#23807)
2022-02-20 11:55:23 -08:00
compile.cc
bigmodel (#23684)
2022-02-19 16:06:31 -08:00
optimizer.cc
thneed: a few asserts in the optimizer for cases it will fail
2022-02-21 12:08:52 -08:00
README
thneed saves 45% of a core (#1512)
2020-05-15 13:53:01 -07:00
serialize.cc
thneed/serialize: use funtions from clutil(#22760)
2021-11-04 16:19:25 +01:00
thneed.cc
add thneed optimizer (#23772)
2022-02-15 15:32:00 -08:00
thneed.h
add thneed optimizer (#23772)
2022-02-15 15:32:00 -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.
Reference in New Issue View Git Blame Copy Permalink