jgrusewski 6f645df11f feat(rl): wire lobsim book data from GPU SoA — proper rewards in GPU loader path ...

Add apply_snapshot_from_device to RlLobBackend: DtoD copy from
perception SoA buffers into lobsim book arrays + book_update kernel.
No host roundtrip, no sync (stream-ordered).

step_with_lobsim_gpu now calls apply_snapshot_from_device with batch 0's
last-snapshot (K-1) book data. Produces non-zero dones, pnl, wr.

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

2026-05-26 21:29:05 +02:00

..

lob

audit(rust-consts): catch literal-vs-const drift + cleanup BOOK_LEVELS=10

2026-05-24 17:39:40 +02:00

policy

refactor(per-horizon): N_HORIZONS 5→3 — ml-backtesting full propagation

2026-05-22 01:37:23 +02:00

sim

feat(rl): wire lobsim book data from GPU SoA — proper rewards in GPU loader path

2026-05-26 21:29:05 +02:00

action_loader.rs

fix(clippy): apply cargo clippy --fix across workspace

2026-03-10 11:17:51 +01:00

aggregate.rs

fix(ml-backtesting): aggregator supports P6 batched output layout

2026-05-19 19:07:35 +02:00

artifacts.rs

feat(ml-backtesting): max_drawdown_pct + deployability verdict emitter (X16+X17)

2026-05-19 08:44:46 +02:00

barrier_backtest.rs

fix(clippy): resolve all clippy warnings across entire workspace (--all-targets)

2026-03-13 10:18:35 +01:00

harness.rs

refactor(rl): FRD horizons + range_σ are ISV-driven, not literals

2026-05-24 19:23:39 +02:00

lib.rs

feat(ml-backtesting): artifacts + sweep aggregate + fxt-backtest CLI (C9)

2026-05-18 08:59:41 +02:00

order.rs

feat(ml-backtesting): host-side order types + SlotTag

2026-05-18 08:11:50 +02:00

report.rs

fix(clippy): achieve zero warnings across entire workspace

2026-03-10 13:18:57 +01:00