Kristian MyramandClaude Sonnet 5.5 5c7eb3c2ae S2.62: GPU encoder (wgpu): Hiera + neck on any GPU, matches PyTorch to 7e-6 ...

Strided batched matmul with bias, GELU/ReLU and residual in the epilogue, layer
norm, softmax, window partition, pooling, patch embedding, RoPE and neck kernels
(WGSL, all tested against CPU definitions). GpuEncoder keeps activations on the
GPU and returns the 64x64 level and the decoder's skip features. On the RX 7900
GRE one frame encodes in 0.29 s (debug build) against 2.1 s on the CPU in release;
errors 6.8e-6 vs PyTorch, 1.2e-5 vs the CPU path.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

2026-10-30 08:43:31 +01:00

..

figure.rs

S2.65: prompt SAM 2 with a box from the classic matte on stroke frames

2026-10-30 08:43:31 +01:00

reference.rs

S2.62: GPU encoder (wgpu): Hiera + neck on any GPU, matches PyTorch to 7e-6

2026-10-30 08:43:31 +01:00