jgrusewski e4870ea5e9 perf(cuda): make GPU eval default, eliminate all mid-loop GPU→CPU transfers ...

- Flip --gpu-eval default to true (--no-gpu-eval to opt out)
- Move actions_history scatter-write into env kernel (zero CPU accumulation)
- Remove done-flag periodic download (env kernel handles per-thread)
- Only GPU→CPU transfer is final metrics readback (n_windows × 40 bytes)
- Add spread cost discrepancy warning when GPU path is active

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-11 15:03:03 +01:00

..

baseline_common

fix(ml): wire spread_cost_bps into RL training — commission + spread = total tx cost

2026-03-01 22:10:43 +01:00

cuda_test.rs

chore: clean up examples, update ML binaries and risk tests

2026-02-27 01:33:18 +01:00

download_baseline.rs

fix(ml): remove dead parquet path, enable GPU features by default

2026-03-10 16:54:45 +01:00

evaluate_baseline.rs

perf(cuda): make GPU eval default, eliminate all mid-loop GPU→CPU transfers

2026-03-11 15:03:03 +01:00

evaluate_supervised.rs

fix(ml): remove dead parquet path, enable GPU features by default

2026-03-10 16:54:45 +01:00

hyperopt_baseline_rl.rs

feat(dqn): Branching DQN + KernelWeightPack + metrics propagation

2026-03-11 00:46:53 +01:00

hyperopt_baseline_supervised.rs

fix(ml): remove dead parquet path, enable GPU features by default

2026-03-10 16:54:45 +01:00

train_baseline_rl.rs

feat(dqn): Branching DQN + KernelWeightPack + metrics propagation

2026-03-11 00:46:53 +01:00

train_baseline_supervised.rs

fix(ml): remove dead parquet path, enable GPU features by default

2026-03-10 16:54:45 +01:00