ayo
7c5d3c9157
Add native K/M/RR inference engines, HIP kernels, replay and validation harnesses, and Windows DLSS setup and runtime support. Include GPU profiling tools, build and packaging scripts, platform integration patches, and implementation documentation.
8 lines
294 B
Plaintext
8 lines
294 B
Plaintext
// fast numerics: intermediate activations f16 (no FP8 re-quantisation), f32 accumulation through GEMM chains
|
|
#define SWIN_NO_Q8
|
|
#define SWIN_F32ACC
|
|
#define SWIN_MAX_VGPR 192
|
|
#define SWIN_MLP_R(NW) 2
|
|
#include "swin_block.h"
|
|
SWIN_MODULE_W(rrlite_dec2_4x4, 96, 4, 8, 0, false, CommonParams, 128)
|