jgrusewski 1f58fee924 feat(rl): wire encoder context broadcast into forward path ...

Completes P2 by injecting rl_encoder_context_broadcast launch inside
the perception trainer's forward_only path — runs after
snap_feature_assemble fills dims [0..40] and before VSN/Mamba2
consume the window tensor. Fills dims [40..56] with per-batch
trade_context (4) + multires (12) features.

Device pointers to the context buffers (owned by IntegratedTrainer)
are set on PerceptionTrainer before each forward_encoder call. The
broadcast kernel reads these and writes directly into window_tensor_d
at the correct column offsets for all B×K rows.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-24 22:46:18 +02:00

..

cuda

feat(rl): encoder input expansion 40 → 56 dims (trade-context + multires)

2026-05-24 22:35:26 +02:00

examples

feat(rl): exhaustive diag JSONL for all trade-management mechanics

2026-05-24 22:05:24 +02:00

src

feat(rl): wire encoder context broadcast into forward path

2026-05-24 22:46:18 +02:00

tests

feat(rl): trade-context + multires features + P14 validation tests

2026-05-24 22:21:30 +02:00

build.rs

feat(rl): encoder input expansion 40 → 56 dims (trade-context + multires)

2026-05-24 22:35:26 +02:00

Cargo.toml

feat(rl): R6 — replace LobEnv with kernel-driven GPU-pure env step

2026-05-23 10:39:25 +02:00