woutermans 607035aa98 Merge PR #26: RDNA4 token-lane Swin and hardware FP8 texture tails ...

# Conflicts:
#	kernels/m/rrlite_enc3_tube_4x4.hip

2026-10-07 22:26:30 +02:00

..

common

Port K kernel tuning and M gfx1101 flags

2026-10-05 14:48:37 -04:00

k

Port K kernel tuning and M gfx1101 flags

2026-10-05 14:48:37 -04:00

m

Merge PR #26: RDNA4 token-lane Swin and hardware FP8 texture tails

2026-10-07 22:26:30 +02:00

native

Add MicroCUDA backend, adaptive output wait, wider native K coverage (improve perf)

2026-10-07 15:54:38 -04:00

support

Add experimental preset L and fix DLSS resource lifetimes and waits

2026-10-02 00:30:46 -04:00

tex

Hardware e4m3 decode in dec0's tail on the native-FP8 build

2026-10-07 01:15:36 +02:00

tools

Add MicroCUDA backend, adaptive output wait, wider native K coverage (improve perf)

2026-10-07 15:54:38 -04:00

build.sh

Add MicroCUDA backend, adaptive output wait, wider native K coverage (improve perf)

2026-10-07 15:54:38 -04:00