StarPilot

mirror of https://github.com/firestar5683/StarPilot.git synced 2026-07-01 03:22:07 +08:00

Files

T

Harald Schäfer f6885dcbec Revert Tinygrad (#34243 )

* Revert "dmonitoringmodeld: use cl transform (#34235)"

This reverts commit 684b0b9d4d.

* Revert "load model before calling convert_fp16_to_fp32"

This reverts commit 31606a7d15.

* Revert "bump tinygrad"

This reverts commit 44f58ff758.

* Revert "Tinygrad runner (#34171)"

This reverts commit 7b5a4fbb03.

* Allow init buffer

* typo

2024-12-14 12:15:36 -08:00

__init__.py

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -08:00

README

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -08:00

serialize.cc

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -08:00

thneed_common.cc

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -08:00

thneed_pc.cc

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -08:00

thneed_qcom2.cc

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -08:00

thneed.h

Revert Tinygrad (#34243 )

2024-12-14 12:15:36 -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.