2c2b62639e
Two complementary changes to reduce clean workspace build time from
~13min to ~8:43:
1. Per-package codegen-units overrides
Default for all release builds: codegen-units = 16 (parallel LLVM).
Numerical-sensitive crates (ml-* family, ndarray, nalgebra, cudarc,
simba, etc.) override back to 1 to preserve bit-exact LLVM
optimization decisions for the DQN regression suite.
Non-numerical plumbing (arrow, sqlx, tokio, parquet, ...) compiles
in parallel via 16 CGUs, no numerical impact.
2. Dependency deduplication
- axum 0.7 → 0.8 (workspace + services/api): dedupes vs tonic 0.14's
transitive axum 0.8. Eliminates a full duplicate compile of axum
and axum-core.
- statrs 0.17 → 0.18: dedupes nalgebra 0.32 vs 0.33. Also closes a
numerical concern (two nalgebra versions linked simultaneously).
- governor 0.6 → 0.10 (services/api + crates/data): dedupes dashmap
5 vs 6. dashmap is heavy; eliminating one full compile is a real
win.
- hashbrown 0.14 → 0.16 (workspace): partial dedupe (dashmap 6.1
still pulls 0.14 transitively).
- Workspace Cargo.toml documents residual unfixable duplicates with
reasons (base64, chacha20, phf, darling, itertools, getrandom,
hashbrown, syn, thiserror — all blocked by third-party crates we
can't bump without breakage).
Verified: cargo check --workspace passes. Numerical crates remain
at codegen-units = 1 — DQN bit-exact reproducibility preserved.
Foxhunt
Production HFT trading system in Rust.
Architecture
The workspace contains 32 crates organized as follows:
Core Libraries (16)
| Crate | Purpose |
|---|---|
trading_engine |
Order processing, FIX 4.4, IB TWS, SIMD, RDTSC timing |
risk |
VaR, Kelly, circuit breakers, kill switches, compliance |
risk-data |
Risk data types and shared structures |
trading-data |
Trading data types |
ml |
DQN Rainbow, PPO, TFT, Mamba2, ensemble inference |
ml-data |
ML data types and feature definitions |
data |
Market data ingestion and storage |
backtesting |
Replay engine, strategy tester |
adaptive-strategy |
Ensemble execution, microstructure analysis |
common |
Shared types, resilience, error handling |
storage |
S3 and local model storage |
model_loader |
Model serialization and loading |
market-data |
Market data feed handlers |
database |
PostgreSQL access layer (SQLx) |
config |
Configuration management |
tli |
CLI commands and tooling |
Services (8)
| Service | Purpose |
|---|---|
backtesting_service |
gRPC backtesting service |
broker_gateway_service |
FIX routing, broker connectivity |
trading_service |
Core trading operations |
ml_training_service |
Model training orchestration |
data_acquisition_service |
Market data acquisition |
trading_agent_service |
Autonomous trading agents |
api_gateway |
gRPC API gateway with auth |
web-gateway |
Axum REST + WebSocket gateway |
Frontend
web-dashboard/ -- React 19 + TypeScript + Vite + TradingView charts.
Building
# Check compilation (no PostgreSQL required)
SQLX_OFFLINE=true cargo check --workspace
# Run tests for a specific crate
SQLX_OFFLINE=true cargo test -p <crate> --lib
# Clippy
SQLX_OFFLINE=true cargo clippy --workspace
ML Models
Four production model architectures on Candle v0.9.1 with CUDA:
- DQN Rainbow -- Deep Q-Network with prioritized replay, dueling heads, noisy nets
- PPO -- Proximal Policy Optimization with GAE and LSTM policies
- TFT -- Temporal Fusion Transformer for multi-horizon forecasting
- Mamba2 -- State space model for sequence prediction
Each model has a standalone trainer and a UnifiedTrainable adapter for the hyperopt pipeline.
Infrastructure
- Git: Gitea at
git.fxhnt.ai(Tailscale-only), Scaleway DEV1-S - Observability: OpenTelemetry OTLP (env
OTEL_EXPORTER_OTLP_ENDPOINT) - Database: PostgreSQL with SQLx offline mode for CI
License
Proprietary. All rights reserved.