foxhunt/crates/ml/Cargo.toml

[package]
name = "ml"
version.workspace = true
edition.workspace = true
rust-version.workspace = true
authors.workspace = true
license.workspace = true
repository.workspace = true
homepage.workspace = true
documentation.workspace = true
publish.workspace = true
keywords.workspace = true
categories.workspace = true

[features]
# MINIMAL features for HFT inference only - ALL HEAVY ML REMOVED
# CUDA is now default for training - GPU acceleration mandatory
default = ["minimal-inference", "cuda"]

# PRODUCTION FEATURES - LIGHTWEIGHT ONLY
minimal-inference = []  # Minimal inference with no optional deps
financial = []  # Basic financial calculations
high-precision = ["rust_decimal/serde-float"]

# PERFORMANCE FEATURES - NO HEAVY ML
mimalloc-allocator = ["mimalloc"]  # Fast memory allocator for 10-25% speedup
simd = []  # SIMD without heavy dependencies

# Storage and memory management features
gc = []  # Garbage collection features
s3-storage = ["aws-config", "aws-sdk-s3", "aws-types", "aws-credential-types", "urlencoding"]  # S3 storage backend with AWS SDK
cuda = ["candle-core/cuda", "candle-core/cudnn", "candle-nn/cuda", "candle-nn/cudnn"]  # CUDA support (includes LSTM sigmoid ops) - OPTIONAL for CI/Docker
nccl = ["cuda"]  # NCCL multi-GPU data parallelism (requires NCCL library + cudarc nccl feature)

# ALL HEAVY ML FEATURES REMOVED:
# gpu, pytorch, linfa-ml - MOVED TO ml_training_service
# optimization, graph-models, reinforcement-learning - MOVED TO ml_training_service
# transformers-advanced - MOVED TO ml_training_service

[dependencies]
# Core async and utilities
tokio.workspace = true
futures.workspace = true
async-trait.workspace = true
clap.workspace = true  # CLI argument parsing for train_tft binary

# Serialization and error handling
serde.workspace = true
serde_json.workspace = true
serde_yaml = "0.9"  # YAML serialization for hyperparameter exports
toml.workspace = true
uuid.workspace = true
thiserror.workspace = true
anyhow.workspace = true
chrono.workspace = true
chrono-tz = "0.10"  # Timezone support for market hours calculations (Wave C)
csv = "1.3"  # CSV serialization for action export (Wave 3 Task 3.1)
rand.workspace = true
rand_chacha = "0.3"  # ChaCha RNG for reproducible Monte Carlo permutation tests

# System and I/O
memmap2.workspace = true
tempfile.workspace = true
tracing.workspace = true
tracing-subscriber.workspace = true  # For train_tft binary logging
prometheus.workspace = true
reqwest.workspace = true
colored = "2.1"  # Terminal color output for evaluation reports

# Internal workspace crates
trading_engine.workspace = true
config.workspace = true
common.workspace = true
risk = { path = "../risk" }
# Model loading functionality is in storage crate
storage = { path = "../storage" }
# Data crate for test helpers (dev-dependency in tests)
data = { path = "../data" }

# Database for model registry
sqlx.workspace = true


# Essential ML frameworks for HFT inference - CUDA OPTIONAL
# Using specific git rev (671de1db) for cudarc 0.17.3 CUDA 13.0 compatibility
# Rev 671de1db is v0.9.1 + cudarc 0.17.3 upgrade
# CUDA features are optional - controlled by 'cuda' feature flag
candle-core = { git = "https://github.com/huggingface/candle", rev = "671de1db" }  # Base without GPU
candle-nn = { git = "https://github.com/huggingface/candle", rev = "671de1db" }
# Use git version of candle-optimisers to match candle version
candle-optimisers = { git = "https://github.com/KGrewal1/optimisers" }  # Base without GPU

# HEAVY ML FRAMEWORKS REMOVED - MOVED TO ml_training_service
# ort (ONNX Runtime) - REMOVED (1000+ dependencies alone!)
# tch, torch-sys (PyTorch bindings) - REMOVED (500+ dependencies!)


# Mathematical libraries
# BLAS feature temporarily disabled - requires libopenblas-dev installation
# TODO: Re-enable after running: sudo apt-get install -y libopenblas-dev
ndarray = { workspace = true, features = ["rayon"] }
nalgebra = { version = "0.33", features = ["serde-serialize"] }

# MINIMAL statistics only - ALL HEAVY ML ALGORITHMS REMOVED
# linfa ecosystem (linfa, linfa-clustering, linfa-linear, linfa-reduction) - REMOVED (200+ deps)
# smartcore - REMOVED (100+ dependencies)
# Basic statistics - always included (not optional)
statrs.workspace = true  # Required for statistical computations


rust_decimal.workspace = true


# gymnasium, rerun - REMOVED (RL frameworks moved to ml_training_service)


# cudarc, wgpu - REMOVED (GPU frameworks moved to ml_training_service)
rayon.workspace = true
crossbeam = { version = "0.8", features = ["std"] }


petgraph = { version = "0.6", features = ["serde"] }  # Required for TGNN graphs
semver = "1.0"
lru.workspace = true  # Required for model caching



# chronoutil, ta, polars - REMOVED or moved to workspace dependencies


# argmin, nlopt, ipopt - REMOVED (optimization frameworks moved to ml_training_service)


half = { version = "2.6.0", features = ["serde"] }
rand_distr.workspace = true
dbn.workspace = true  # Databento Binary format for real market data loading
databento = "0.34"  # Databento API client for downloading data (includes async by default)

# Performance allocators
mimalloc = { version = "0.1", optional = true }  # Fast memory allocator
dotenv = "0.15"  # Load .env files for API keys
parking_lot = { version = "0.12", features = ["hardware-lock-elision"] }
dashmap = { workspace = true }
once_cell = "1.19"
lazy_static.workspace = true
flate2 = "1.0"
sha2 = "0.10"
hmac = "0.12"  # HMAC for checkpoint signatures (SEC-001 fix)
hex = "0.4"    # Hex encoding for signatures
bincode = "1.3"
fastrand = "2.1"
# wide - REMOVED (SIMD moved to trading_engine)
num-traits = "0.2"

# Parquet I/O for feature caching (Wave 2 Agent 8)
# Updated to workspace version 56 to fix arrow-arith compilation conflict
parquet.workspace = true
arrow.workspace = true
bytes = "1.5"  # For Parquet in-memory serialization
num = "0.4"
libc = "0.2"
fs2 = "0.4"
num_cpus = "1.16"
approx.workspace = true
sysinfo = "0.33"  # System information for benchmarks

# AWS SDK dependencies for S3 checkpoint storage (optional, s3-storage feature)
aws-config = { version = "1.1", optional = true }
aws-sdk-s3 = { version = "1.14", optional = true }
aws-types = { version = "1.1", optional = true }
aws-credential-types = { version = "1.1", optional = true }
urlencoding = { version = "2.1", optional = true }

# Bayesian optimization for hyperparameter tuning (using argmin instead of egobox due to ndarray conflict)
argmin = { version = "0.8", features = ["rayon"] }  # Optimization framework with parallel execution
argmin-math = "0.3"  # Math utilities for argmin

[dev-dependencies]
tokio-test = "0.4"
proptest = "1.5"
tempfile = "3.12"
futures-test = "0.3"
test-case = "3.0"
rstest = "0.22"
criterion = { version = "0.5", features = ["html_reports", "async_tokio"] }
fastrand = "2.1"

tokio = { workspace = true, features = ["test-util", "macros"] }
insta = "1.34"  # Snapshot testing for ML outputs
serial_test = "3.0"  # Sequential testing for GPU resources
tracing-subscriber = { version = "0.3", features = ["env-filter", "fmt"] }
rand_chacha = "0.3"  # ChaCha RNG for hyperopt tests

[[example]]
name = "cuda_test"
path = "examples/cuda_test.rs"

[[example]]
name = "train_baseline_rl"
path = "examples/train_baseline_rl.rs"

[[example]]
name = "train_baseline_supervised"
path = "examples/train_baseline_supervised.rs"

[[example]]
name = "evaluate_baseline"
path = "examples/evaluate_baseline.rs"

[[example]]
name = "hyperopt_baseline_rl"
path = "examples/hyperopt_baseline_rl.rs"

[[example]]
name = "hyperopt_baseline_supervised"
path = "examples/hyperopt_baseline_supervised.rs"

[[bench]]
name = "microstructure_bench"
harness = false

[[bench]]
name = "alternative_bars_bench"
harness = false

[[bench]]
name = "bench_feature_extraction"
harness = false

[lints]
workspace = true