mirror of
https://github.com/storytold/lightcraft.git
synced 2026-10-26 02:59:17 -06:00
Andrew FrahnandClaude Opus 5.5
0242a75b5a
An accelerator hook in the face interpreter takes Conv nodes; lightcraft-gpu implements it with a WGSL implicit-GEMM convolution (any stride, padding, grouping; split-K for small maps; a direct kernel for depthwise layers), each model's weights resident on a device of its own. After loading, detection and recognition check the GPU in the background (agreement within 1e-3 and faster than the CPU) and otherwise stay on the CPU, which remains the reference; the first GPU error drops it. Sources: own design. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>