gitadmin/foxhunt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
2,076 Commits 13 Branches 0 Tags
a5ea8713b6dced628a58ed0113da08d28debd475
Commit Graph

8 Commits

Author SHA1 Message Date
jgrusewski
a5ea8713b6 feat(dqn): Branching DQN + KernelWeightPack + metrics propagation 
Branching DQN (Tavakoli et al., 2018):
- 3 independent advantage heads (exposure=5, order=3, urgency=3) in CUDA kernel
- `use_branching` as hyperopt-tunable parameter (index 11 in 29D space)
- Branch weight pointers packed into KernelWeightPack struct

KernelWeightPack refactor:
- 87→38 CUDA kernel params by packing 48 weight pointers into 384-byte #[repr(C)] struct
- UNPACK_WEIGHT_PTRS macro in CUDA header for clean kernel-side access
- Single .arg(&weight_pack) replaces 48 individual .arg() calls

Hyperopt metrics in JSON output:
- Added `metrics: Option<serde_json::Value>` to TrialResult<P>
- `extract_metrics()` trait method with default None (DQN overrides)
- JSON output now includes per-trial backtest metrics (Sharpe, Sortino,
  Calmar, Omega, drawdown, win_rate, trades) + top-level best_metrics

Prometheus backtest gauges (Rust-side, no CUDA):
- 8 new gauges: foxhunt_hyperopt_best_{sharpe,sortino,calmar,omega,
  max_drawdown_pct,win_rate,total_trades,total_return_pct}

Dynamic episode scaling:
- Removed hardcoded 256 episode cap on small GPUs
- VRAM budget calculation in optimal_n_episodes() handles scaling naturally
- Removed stale .min(256) in PPO trainer

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-11 00:46:53 +01:00
jgrusewski
7d1b0f232f refactor(ml): move core types to ml-core + dedup MLError (5a) 
Move all inline type definitions from ml/src/lib.rs to ml-core:
MLError, MLResult, Trade, MarketRegime, HealthStatus, Features,
MLModel trait, ModelRegistry, ParallelExecutor, LatencyOptimizer,
TrainingMetrics, ValidationMetrics, InferenceResult, ModelMetadata.

Dedup: consolidate ConfigError{reason}/ConfigurationError(msg) into
single ConfigError(String) tuple variant (was 2 variants, 174 refs).

Cleanup: convert create_hft_* free functions to associated methods
(HFTPerformanceProfile::ultra_low_latency(), ParallelExecutor::hft()).

ml facade re-exports via `pub use ml_core::*`.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-08 15:13:41 +01:00
jgrusewski
2aedc2ae1a feat(ml): comprehensive GPU saturation audit — 58 fixes across all 10 models 
Phase 1 — Fix broken models (P0):
- Diffusion: wire optimizer_step to actually apply gradients (was no-op)
- TLOB: connect forward pass to projection layers (was Tensor::zeros)
- Mamba2: F64→F32 migration across 5 files (~30x faster on L40S tensor cores)

Phase 2 — Eliminate hot-path GPU sync stalls:
- Mamba2: keep dt on GPU in discretize_ssm (4 functions, no CPU round-trip)
- TFT: gate attention weight logging to eval only (8 syncs/forward eliminated)
- Mamba2: defer loss scalar after backward (pipeline stall removed)
- Mamba2: delete dead gradient clipping (4N wasted GPU syncs removed)

Phase 3 — Enable BF16 for supervised models:
- Flip mixed_precision defaults to true in 4 config locations
- Fix cuda_layer_norm to support BF16/F16 via F32 intermediate

Phase 4 — Raise hyperopt bounds for datacenter GPUs:
- 7 adapters with VRAM-aware tiers (TFT, Liquid, TGGN, KAN, xLSTM,
  Diffusion, TLOB) — L40S gets full hidden_dim range
- Fix L40S tier boundary (was excluded at <48000, now >=40000)

Phase 5 — Update memory estimates:
- 10 param_count estimates updated (DQN 200K→12M, TFT 2M→50M, etc.)
- Fix power-of-two rounding (was wasting up to 49% of budget)
- Correct MODEL_OVERHEAD_MB in DQN/PPO/TFT adapters

Phase 6 — Fix per-epoch CPU bottlenecks:
- PPO: deduplicate double advantage normalization (correctness fix)
- PPO: GPU tensor reward normalization + explained variance
- Fuse per-parameter grad norm to single GPU sync (xLSTM, KAN, TGGN)

Phase 7 — Data pipeline:
- GpuBufferPool: use from_slice (eliminate staging buffer copy)

Phase 8 — Correctness:
- TFT: remove broken .detach() in forward_checkpointed (restore gradients)
- Update stale RTX 3050 Ti doc references

33 files changed, 2451 tests pass, 0 clippy warnings.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-02 15:41:23 +01:00
jgrusewski
4a3f387860 fix(ml): Arc<Vec<OHLCVBar>> → Arc<[OHLCVBar]> in hyperopt adapters 
Fixes clippy::rc_buffer lint in 8 hyperopt adapter files.
Arc<[T]> avoids double indirection vs Arc<Vec<T>>.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-01 20:59:21 +01:00
jgrusewski
2b2ff4ffa5 feat(ml): maximize GPU utilization — BF16 mixed precision, dynamic sizing, sync reduction 
Wire BF16/FP16 mixed precision end-to-end for DQN and PPO with auto-detection
from GPU name (Ampere+ → BF16, Volta/Turing → FP16). Add hidden_dim_base to
hyperopt and wire through training/eval binaries. Reduce GPU sync points: make
DQN NaN checks periodic (every 100 steps), replace PPO GAE GPU round-trip with
pure CPU implementation. Cache training data across hyperopt trials for all 10
models via Arc. Batch DQN experience storage (128x fewer lock acquisitions).
Correct VRAM constants and batch bounds for all 9 supervised model adapters.

28 files changed, +1207/-208 lines. 2418 tests pass.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-01 17:54:25 +01:00
jgrusewski
b4239e8c43 feat(hyperopt): add VRAM-aware batch_size scaling to 9 existing adapters 
Override continuous_bounds_for() in all adapters that already have batch_size:
- TFT (idx 1): 150MB overhead, 0.05 MB/sample, cap 2048
- Mamba2 (idx 1): 200MB overhead, 0.03 MB/sample, cap 2048
- TGGN (idx 7): 100MB overhead, 0.08 MB/sample, cap 1024
- TLOB (idx 6): 120MB overhead, 0.10 MB/sample, cap 1024
- KAN (idx 7): 80MB overhead, 0.04 MB/sample, cap 1024
- xLSTM (idx 6): 180MB overhead, 0.06 MB/sample, cap 1024
- Diffusion (idx 6): 250MB overhead, 0.12 MB/sample, cap 512
- DQN (idx 1): 300MB overhead, 0.02 MB/sample, cap 4096
- ContinuousPPO (idx 9): 250MB overhead, 0.03 MB/sample, cap 4096

On CPU-only, all adapters fall back to existing static bounds.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-28 19:19:25 +01:00
jgrusewski
b09ebfc3cb feat(ml): add HyperparameterOptimizable trainers for all 8 supervised models 
Extend hyperopt infrastructure to support all 10 ML models (DQN, PPO +
8 supervised). Previously only TFT and Mamba2 had hyperopt trainers.

- Add HyperparameterOptimizable impl for Liquid, TGGN, TLOB, KAN, xLSTM, Diffusion
- Create shared_data.rs with common data prep utilities (build_flat_pairs,
  build_sequence_pairs, write_trial_result_json)
- Extend hyperopt_baseline_supervised binary to dispatch all 8 models
  (individual, "both" for tft+mamba2, "all" for all 8)
- Add CI jobs: 7 train-validate + 10 hyperopt jobs for all models
- Fix DiffusionMetrics NaN default, XLSTMMetrics serde, safe indexing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-26 23:47:52 +01:00
jgrusewski
9c3d741a08 refactor: restructure repo — crates/, bin/, testing/ layout 
Move 17 library crates into crates/, CLI binary into bin/fxt,
consolidate 10 test crates into testing/, split config crate
from deployment config files.

Root directory reduced from 38+ to ~17 directories.
All Cargo.toml paths and build.rs proto refs updated.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-25 11:56:00 +01:00