jgrusewski 11eb74766a feat(per-horizon-cfc): add cfc_step_per_branch.cu (fused fwd+bwd) ...

Per spec §5.4 point 1. Single fused kernel: grid=(B, N_HORIZONS, 1),
block=(MAX_BUCKET_DIM=28, 1, 1) uniform predicate. Shared x_local +
h_old_local cooperative-staged into shared memory once per block per
pearl_cooperative_staging_eliminates_redundant_reads. No atomicAdd.
No host branches.

Forward GPU oracle: matches naive per-channel CfC math (tol 1e-4) on
sm_86. Backward smoke: kernel loads + writes non-NaN gradients.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-21 15:56:20 +02:00

..

fixtures

fix(ml-core): deterministic GPU weight init via scoped_init_seed

2026-05-19 01:19:13 +02:00

adamw_invariants.rs

feat(ml-alpha): BCE multi-horizon + AdamW kernels

2026-05-16 21:57:26 +02:00

backward_finite_diff.rs

feat(ml-alpha): cfc_step_backward emits grad_x for upstream chain

2026-05-16 22:59:36 +02:00

bce_grad_finite_diff.rs

refactor(ml-alpha): consolidate BCE — Kendall σ is THE BCE, wire MHA into trainer

2026-05-18 14:59:12 +02:00

bucket_transition_kernels.rs

feat(per-horizon-cfc): add bucket_transition_kernels.cu (5 device kernels)

2026-05-21 15:46:56 +02:00

cfc_step_bit_equiv.rs

feat(ml-alpha): cfc_step kernel + invariant-based GPU validation

2026-05-16 21:50:20 +02:00

cfc_step_per_branch.rs

feat(per-horizon-cfc): add cfc_step_per_branch.cu (fused fwd+bwd)

2026-05-21 15:56:20 +02:00

forward_graph_capture.rs

feat(ml-alpha): CUDA Graph capture of forward_only (P5)

2026-05-19 17:32:28 +02:00

forward_step_golden.rs

test(crt-a): buffer-level seed bit-identity replaces prediction-level test

2026-05-20 19:10:47 +02:00

gpu_log_ring_invariants.rs

fix(gpu-log): use std::thread for drain task (no tokio runtime needed)

2026-05-21 02:08:55 +02:00

heads_bit_equiv.rs

feat(ml-alpha): multi_horizon_heads kernel (128->5 sigmoid)

2026-05-16 21:51:48 +02:00

isv_bus.rs

…

multi_horizon_loader.rs

refactor(per-horizon-cfc): atomically remove MTER scaffolding

2026-05-21 15:36:28 +02:00

output_smoothness_grad_finite_diff.rs

test(crt-train): finite-diff validate output_smoothness kernel grad

2026-05-20 23:31:40 +02:00

perception_forward_golden.rs

fix(ml-core): deterministic GPU weight init via scoped_init_seed

2026-05-19 01:19:13 +02:00

perception_overfit.rs

refactor(per-horizon-cfc): atomically remove MTER scaffolding

2026-05-21 15:36:28 +02:00

pinned_slots.rs

…

projection_bit_equiv.rs

feat(ml-alpha): projection kernel (128->8 + layer-norm)

2026-05-16 21:52:57 +02:00

smoothness_lambda_controller_invariants.rs

feat(gpu-log): wire smoothness_lambda_controller as first ring producer

2026-05-21 01:36:18 +02:00

snap_feature_bit_equiv.rs

Revert "arch(ml-alpha): restore count-delta redundancy at feature slot [26]"

2026-05-18 23:16:38 +02:00