jgrusewski a06abf60df test(ml-alpha): synthetic multi-resolution pipeline test ...

Four pure-CPU tests confirming aggregate_window emits the right
ts_ns - prev_ts_ns span per scale, so the existing snap-feature Δt
Fourier encoder gets correctly-scaled inputs without any CUDA kernel
changes.

2026-05-22 20:46:55 +02:00

..

cuda

feat(aux-heads): rewrite for A+B paired (BCE + conditional-Huber) (CB3+CB4)

2026-05-22 11:16:29 +02:00

examples

feat(alpha_train): --multi-resolution CLI flag

2026-05-22 20:42:40 +02:00

src

fix(loader): anchor sampler enforces lookback lower bound

2026-05-22 20:22:16 +02:00

tests

test(ml-alpha): synthetic multi-resolution pipeline test

2026-05-22 20:46:55 +02:00

build.rs

feat(aux-heads): rewrite for A+B paired (BCE + conditional-Huber) (CB3+CB4)

2026-05-22 11:16:29 +02:00

Cargo.toml

refactor(gpu-log): rename feature cuda-diag-log → kernel-step-trace

2026-05-21 01:44:29 +02:00