Fast and generic implementation using OpenMP and CUDA#45

Open

shikishima-TasakiLab wants to merge 14 commits into

d-li14:mainfrom

shikishima-TasakiLab:main

Commits on Jun 12, 2021

First commit
shikishima-TasakiLab
committed

Commits on Jun 13, 2021

CPU-only support
shikishima-TasakiLab
committed
Update README.md
shikishima-TasakiLab
authored

Commits on Jun 27, 2021

Remove "AutoNonVariableTypeMode".
shikishima-TasakiLab
committed
Merge branch 'main' of https://github.com/shikishima-TasakiLab/Involution-PyTorch into main
shikishima-TasakiLab
committed

Commits on Jun 29, 2021

Merge remote-tracking branch 'upstream/main' into main
shikishima
committed

Commits on Jul 4, 2021

Compatible with PyTorch 1.7.0 or later
shikishima-TasakiLab
committed
Update README.md
shikishima-TasakiLab
authored
Merge remote-tracking branch 'upstream/main' into main
shikishima-TasakiLab
committed

Commits on Jul 10, 2021

Fixed the value of CUDA_MAX_THREADS
shikishima-TasakiLab
committed
Fixed auto-casting to float32 when using AMP.
shikishima-TasakiLab
committed
Merge remote-tracking branch 'upstream/main' into main
shikishima-TasakiLab
committed

Commits on Jul 13, 2021

Support fatbin.
shikishima
committed
Merge remote-tracking branch 'upstream/main' into main
shikishima
committed