jgrusewski 67dd414cb3 feat(sp5): Task A4 — Pearl 4 per-group Adam β1/β2/ε ...

Per-param-group Adam hyperparameters from per-group gradient
direction-stability EMA + L2 norm. 8 SP4 param groups × 3 hparams = 24
ISV slots [226..250).

Two-kernel chain:
  grad_cosine_sim_update — per-group cosine_sim of curr vs prev grads
                          + L2 norm; writes back grad_curr → grad_prev
                          for next step's comparison.
  pearl_4_adam_hparams_update — β1/β2/ε from cosine + l2_norm.

Structural envelopes (Invariant 1 anchors per spec line 88):
  β1 ∈ [0.85, 0.95]; β2 ∈ [0.99, 0.9995]; ε ∈ [1e-10, 1e-6]

ALPHA_META migration (Option A — atomic shared-contract migration per
feedback_no_partial_refactor): apply_pearls_ad_kernel.cu and the
launch_apply_pearls Rust wrapper now take alpha_meta as a parameter.
All 45 existing call sites (SP4 + SP5 producers) pass the prior default
1.0e-3 explicitly via crate::cuda_pipeline::sp4_wiener_ema::ALPHA_META.
Pearl 4's apply_pearls calls pass 5.0e-4 (half the default per spec
line 89) to limit β change rate.

Theoretical caveat: adaptive β breaks Adam's constant-β convergence
proof. Mitigations: structural envelopes + halved ALPHA_META + Pearls
A+D smoothing. Fall-back path defined: revert + ε-only adaptive
variant if Layer C destabilization observed.

New mapped-pinned buffer: grad_prev_buf_per_group [TOTAL_PARAMS] for
cosine-sim previous-step direction storage. Mapped-pinned i32 mirror
of grad_buf layout.

producer_step_scratch_buf grew 131 → 171 (40 new outputs: 8 cosine_sim
+ 8 l2_norm + 24 β1/β2/ε). wiener_state_buf already at 543 (A1 sized
for entire SP5 block).

StateResetRegistry: 4 new FoldReset entries: sp5_adam_beta1,
sp5_adam_beta2, sp5_adam_eps, sp5_grad_prev_buf. All sentinel 0 →
bootstrap to envelope midpoint via Pearls A+D + cosine_sim=0 fall-back
on first step of new fold.

Adam-launcher consumer migration deferred to Layer B.

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

2026-05-01 22:18:10 +02:00

..

common

…

edge_cases

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

fixtures

…

integration

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

regression

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

unit

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

validation

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

ab_testing_integration.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

action_loader_real_csv_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

action_masking_smoke_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

activation_tests.rs

fix(tests): update integration tests for f32 pipeline + adam_epsilon

2026-03-29 21:32:04 +02:00

adx_features_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

barrier_optimization_test.rs

…

bayesian_changepoint_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

bessel_correction_test.rs

…

bug16_portfolio_features_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

bug18_cash_reserve_solvency_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

bug20_portfolio_normalization_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

bug21_bug22_bug23_compilation_fixes_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

bug24_bug25_compilation_fixes_test.rs

…

bug28_unused_import_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

cash_accounting_fix_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

cash_reserve_requirement_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

checkpoint_test.rs

…

configurable_capital_test.rs

…

contract_multiplier_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

cusum_test.proptest-regressions

…

debug_position_delta_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

diffusion_integration.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

dqn_accumulation_convergence_test.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

dqn_action_collapse_fix_test.rs

refactor(dqn): strip dead use_* flags + tighten count_bonus API

2026-04-27 17:52:23 +02:00

dqn_action_dependent_reward_test.rs

…

dqn_action_masking_integration_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_action_position_sign_convention_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_activity_penalty_fix_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_adapter_paths_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_advanced_metrics_integration_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_barrier_integration_debug_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_c51_shape_validation_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

dqn_diagnostic_logging_test.rs

fix: migrate 4 DQN/recovery test files to GPU types — 92 errors fixed

2026-03-19 08:55:55 +01:00

dqn_diversity_penalty_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_dueling_batched_wave62_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

dqn_early_stopping_termination_test.rs

refactor(dqn): f64 → f32 for kernel-facing hyperparams

2026-04-24 01:55:14 +02:00

dqn_episode_boundaries_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_epsilon_decay_validation_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_feature_cache_test.rs

chore: rename test_data/mbp10 to mbp10-fixtures, remove uncompressed .dbn

2026-04-01 01:13:19 +02:00

dqn_feature_defaults_test.rs

refactor: remove 8 always-on use_ booleans — features are mandatory

2026-03-25 09:45:54 +01:00

dqn_gradient_accumulation_test.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

dqn_gradient_collapse_root_cause_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_gradient_dtype_simple_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_hft_barriers_test.rs

…

dqn_hyperopt_json_export_test.rs

fix: update 9 test files for 14D DQNParams restructure

2026-03-31 01:30:33 +02:00

dqn_hyperopt_test.rs

fix: update 9 test files for 14D DQNParams restructure

2026-03-31 01:30:33 +02:00

dqn_hyperparams_kelly_fields_test.rs

refactor(dqn): f64 → f32 for kernel-facing hyperparams

2026-04-24 01:55:14 +02:00

dqn_inference_test.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

dqn_kelly_regime_integration_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_logit_clipping_bug12_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

dqn_long_training_test.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

dqn_pnl_calculation_tests.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_rainbow_config_test.rs

refactor(cuda): eliminate all CPU fallbacks — CUDA mandatory across ML stack

2026-03-16 21:01:28 +01:00

dqn_rainbow_test.rs

refactor(cuda): eliminate all CPU fallbacks — CUDA mandatory across ML stack

2026-03-16 21:01:28 +01:00

dqn_regime_conditional_integration_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_reward_calculation_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

dqn_tensor_shape_validation.rs

…

dqn_trainer_integration_tests.rs

fix: update all test/example files for VarStore removal + 7-level exposure

2026-04-11 15:21:21 +02:00

dqn_trainer_p1_tests.rs

cleanup: remove ALL 32 enable_* feature flags — all features unconditional

2026-03-31 10:56:20 +02:00

dqn_training_pipeline_test.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

dqn_transaction_cost_bug2_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_transaction_costs_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

dqn_use_double_dqn_test.rs

refactor: remove 8 always-on use_ booleans — features are mandatory

2026-03-25 09:45:54 +01:00

dropout_scheduler_tests.rs

fix(tests): update integration tests for f32 pipeline + adam_epsilon

2026-03-29 21:32:04 +02:00

ensemble_4_models_integration.rs

…

ensemble_hot_swap_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

ensemble_hyperopt_tests.rs

fix: update 9 test files for 14D DQNParams restructure

2026-03-31 01:30:33 +02:00

ensemble_inference_integration_test.rs

refactor: remove configurable state_dim — use STATE_DIM constant everywhere

2026-04-20 15:29:05 +02:00

evaluation_net_pnl_bug3_test.rs

…

feature_extraction_46_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

feature_normalization_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

fxcache_roundtrip_test.rs

feat(fxcache): OFI_DIM 20→32, persist 12 real-math microstructure signals,

2026-04-23 11:36:34 +02:00

gpu_backtest_validation.rs

refactor: eliminate ALL bf16 from entire workspace — pure f32/TF32 pipeline

2026-04-10 18:52:21 +02:00

gpu_per_integration_test.rs

refactor: remove configurable state_dim — use STATE_DIM constant everywhere

2026-04-20 15:29:05 +02:00

gradient_accumulation_tests.rs

refactor: remove 8 always-on use_ booleans — features are mandatory

2026-03-25 09:45:54 +01:00

huber_loss_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

hyperopt_action_masking_test.rs

cleanup: remove ALL 32 enable_* feature flags — all features unconditional

2026-03-31 10:56:20 +02:00

hyperopt_early_stopping_infrastructure_test.rs

…

hyperopt_kelly_params_test.rs

fix: update 9 test files for 14D DQNParams restructure

2026-03-31 01:30:33 +02:00

hyperopt_paths_test.rs

…

hyperopt_price_extraction_test.rs

…

hyperopt_tft_early_stopping_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

imbalance_bars_test.rs

…

inference_engine_test.rs

…

integration_ppo_ensemble.rs

…

kan_integration.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

kelly_criterion_integration_test.rs

…

liquid_cfc_training_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

liquid_networks_test.rs

…

liquid_nn_training_tests.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

log_size_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

lr_scheduler_tests.rs

…

mamba2_accuracy_fix_test.rs

fix: migrate remaining 8 test files to GPU types — all test errors fixed

2026-03-19 08:59:52 +01:00

mamba2_early_stopping_test.rs

fix: wire real GPU backprop + SPSA gradients, fix checkpoint loading, eliminate candle from examples

2026-03-20 15:41:42 +01:00

mamba2_gradient_extraction_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

mamba2_hyperopt_edge_cases.rs

refactor: eliminate candle from entire workspace — tests, examples, Cargo.toml

2026-03-18 00:53:47 +01:00

mamba2_hyperopt_p0_p1_fixes.rs

…

mamba2_weight_update_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

mbp10_parsing_test.rs

chore: rename test_data/mbp10 to mbp10-fixtures, remove uncompressed .dbn

2026-04-01 01:13:19 +02:00

microstructure_features_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

model_registry_checkpoint_test.rs

…

model_validation_comprehensive.rs

…

moe_kernels_test.rs

feat(moe): adaptive load-balance λ via gate-entropy ISV controller

2026-04-28 09:10:31 +02:00

multi_cusum_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

ofi_features_test.rs

fix(ofi): align OFI window to bar t's formation interval — kill 31/32-slot lookahead

2026-04-28 09:23:32 +02:00

ood_input_handling_tests.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

pages_test_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

paper_trading_integration_test.rs

refactor: remove configurable state_dim — use STATE_DIM constant everywhere

2026-04-20 15:29:05 +02:00

partial_reversal_support_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

partial_reversal_validation.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

pnl_realism_tests.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

portfolio_integration_tests.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

portfolio_tracker_reset_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

portfolio_value_normalization_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

ppo_45_action_network_tests.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

ppo_action_masking_tests.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

ppo_checkpoint_roundtrip_test.rs

fix: migrate remaining 8 test files to GPU types — all test errors fixed

2026-03-19 08:59:52 +01:00

ppo_circuit_breaker_tests.rs

…

ppo_continuous_bounds_test.rs

…

ppo_continuous_transaction_costs_tests.rs

…

ppo_dual_phase_backtest_tests.rs

…

ppo_entropy_regularization_tests.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

ppo_factored_action_tests.rs

fix: update all test/example files for VarStore removal + 7-level exposure

2026-04-11 15:21:21 +02:00

ppo_hidden_state_tests.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

ppo_huber_loss_validation.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

ppo_hyperopt_validation_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

ppo_long_training_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

ppo_lstm_architecture_tests.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

ppo_lstm_training_loop_tests.rs

cleanup: declarative rewrites for ml-tests and trading-engine TODOs

2026-04-23 08:44:05 +02:00

ppo_portfolio_tracker_tests.rs

…

ppo_position_limits_tests.rs

…

ppo_recurrent_integration_tests.rs

cleanup: declarative rewrites for ml-tests and trading-engine TODOs

2026-04-23 08:44:05 +02:00

ppo_recurrent_performance_tests.rs

refactor: remove gpu_n_episodes override — auto-scale from VRAM everywhere

2026-04-02 14:21:45 +02:00

ppo_reward_normalizer_tests.rs

…

ppo_sequence_batching_multi_episode_tests.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

ppo_step_counter_fix_test.rs

fix: migrate remaining 8 test files to GPU types — all test errors fixed

2026-03-19 08:59:52 +01:00

ppo_stress_testing_tests.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

ppo_transaction_costs_tests.rs

…

ppo_validation_real_data_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

preprocessing_bessel_integration.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

preprocessing_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

preprocessing_validation_tests.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

price_validity_tests.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

production_trainer_adaptive_features_integration_test.rs

…

production_training_smoke_test.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

pso_budget_calculation_test.rs

…

q_value_constraint_test.rs

…

rainbow_loss_shape_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

real_data_helpers.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

real_data_pipeline_test.rs

…

recovery_tests.rs

fix: migrate 4 DQN/recovery test files to GPU types — 92 errors fixed

2026-03-19 08:55:55 +01:00

regime_transition_features_test.rs

…

risk_action_masking_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

risk_position_limit_integration_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

run_bars_test.rs

…

safety_comprehensive_test.rs

…

sample_weights_test.rs

…

scatter_add_gradient_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

smoke_test_real_data.rs

perf(checkpoint): async best-ckpt serialize via spawn_blocking + mapped-pinned param snapshot

2026-04-28 18:54:00 +02:00

softmax_exploration_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

sp4_producer_unit_tests.rs

fix(sp4): #260 — eliminate SP1-era 1e6 × isv multipliers via ISV-driven producers

2026-05-01 12:41:29 +02:00

sp5_producer_unit_tests.rs

feat(sp5): Task A4 — Pearl 4 per-group Adam β1/β2/ε

2026-05-01 22:18:10 +02:00

streaming_pipeline_edge_cases.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

supervised_gpu_smoke_test.rs

fix: supervised GPU smoke test dimension mismatches

2026-03-21 09:14:53 +01:00

target_update_tests.rs

refactor: eliminate ALL bf16 from entire workspace — pure f32/TF32 pipeline

2026-04-10 18:52:21 +02:00

test_dbn_sequence_256_features.rs

fix: migrate remaining 8 test files to GPU types — all test errors fixed

2026-03-19 08:59:52 +01:00

test_dqn_cuda_device.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

test_extract_256_dim_features.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

test_grn_weight_initialization.rs

fix: migrate 3 TFT test files to GPU types — 172 errors fixed

2026-03-19 08:44:50 +01:00

test_scatter_source_gradients.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

test_sell_bug.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

test_streaming_loader.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

test_var_gradient_flow.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

tft_adapter_paths_test.rs

…

tft_causal_masking_validation.rs

fix: migrate 3 TFT test files to GPU types — 172 errors fixed

2026-03-19 08:44:50 +01:00

tft_hyperopt_real_metrics_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

tft_inference_latency_benchmark.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

tft_lru_cache_test.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00

tft_quantile_loss_validation.rs

fix: migrate 3 TFT test files to GPU types — 172 errors fixed

2026-03-19 08:44:50 +01:00

tft_real_dbn_data_test.rs

fix: migrate remaining 8 test files to GPU types — all test errors fixed

2026-03-19 08:59:52 +01:00

tft_test.rs

refactor(ml): delete mixed_precision module — BF16 unconditional on CUDA

2026-03-16 16:11:48 +01:00

training_chaos_tests.rs

fix: tune log levels across workspace — demote noisy warn to debug/trace

2026-03-14 11:35:15 +01:00

training_edge_cases.rs

fix: update all test/example files for VarStore removal + 7-level exposure

2026-04-11 15:21:21 +02:00

transaction_cost_application_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

transition_matrix_test.rs

…

triple_barrier_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

volatility_epsilon_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

wave16_checkpoint_regression_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

wave16q_ohlcv_mutation_test.rs

refactor: all train() and load_training_data() callers pass explicit symbol

2026-04-04 10:02:37 +02:00

wave16r_position_limits_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

wave16s_price_validation_test.rs

refactor: collapse 9-level to 7-level ExposureLevel — eliminate degenerate Flat variants

2026-04-11 11:54:09 +02:00

wave_d_e2e_nq_fut_225_features_enhanced_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

wave_d_e2e_nq_fut_225_features_test.rs

fix(tests): CI GPU test stability, walltime reduction, BF16 tolerance

2026-03-15 12:00:13 +01:00

wave_d_edge_cases_test.rs

…

xlstm_integration.rs

fix: migrate 44 test files from Candle to native CUDA — zero test compile errors

2026-03-19 10:02:26 +01:00