Files
effectcraft/docs
Kristian MyramandClaude Sonnet 5.5 921bb00ba6 S2.61: parallel bias add fused with GELU; GPU matmul spike
Candle adds a bias on one thread; the Linear layers now add it (and apply GELU
for the MLP in) in one parallel pass. Encode 2.4 s -> 2.1 s, memory attention
2.4 -> 2.3 s; reference tests unchanged. gpu_matmul example: a tiled WGSL
matmul on the RX 7900 GRE reaches 1.9-3.6 TFLOPS against 0.16-0.47 for the CPU.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-30 08:43:31 +01:00
..
2026-10-13 14:34:22 +02:00