Files
foxhunt/config/src/ml_config.rs
jgrusewski 83629f9ca8 feat(deployment): Complete Runpod GPU deployment infrastructure
Implement comprehensive Runpod deployment with S3 volume mount architecture for
FP32 ML model training on Tesla V100 GPUs.

## Infrastructure Components

### Deployment Scripts (scripts/)
- runpod_deploy.sh: Master deployment orchestrator (8-step workflow)
- runpod_upload.sh: S3 upload for binaries and test data
- upload_env_to_runpod.sh: Secure .env credentials upload
- runpod_deploy_test.sh: Prerequisites validation

### Docker Configuration
- Dockerfile.runpod: Multi-stage CUDA 12.1 runtime (~2GB, no binaries)
- entrypoint.sh: Volume verification and training execution
- Architecture: Volume mount (NO S3 downloads in pods)

### S3 Configuration
- Bucket: se3zdnb5o4 (Iceland region: eur-is-1)
- Endpoint: https://s3api-eur-is-1.runpod.io
- Structure: binaries/, test_data/, models/, .env

### OpenTofu Infrastructure (terraform/runpod/)
- main.tf: Pod and volume resources
- variables.tf: Configuration variables
- outputs.tf: Pod connection info
- Security: NO credentials in state (uses volume .env)

## Deployment Assets Uploaded

### Training Binaries (77MB)
- train_tft_parquet (23M) - TFT-225 features
- train_mamba2_parquet (22M) - MAMBA-2 state space
- train_dqn (22M) - Deep Q-Network
- train_ppo (13M) - Proximal Policy Optimization

### Test Data (13.8 MB)
- 9 Parquet files: ES.FUT, NQ.FUT, 6E.FUT, ZN.FUT (180-day datasets)

### Credentials
- .env file (1.5 KB, private access, chmod 600)

## Documentation

### Deployment Guides
- RUNPOD_DEPLOYMENT_READY_SUMMARY.md: Complete deployment status
- RUNPOD_VOLUME_DEPLOYMENT_GUIDE.md: Step-by-step guide (42KB)
- RUNPOD_DEPLOYMENT_QUICK_START.md: Quick reference
- RUNPOD_UPLOAD_GUIDE.md: S3 upload instructions
- RUNPOD_VOLUME_CONFIGURATION_COMPLETE.md: S3 setup report
- RUNPOD_S3_PARQUET_UPLOAD_REPORT.md: Data upload verification

### Architecture Documentation
- RUNPOD_VOLUME_MOUNT_ARCHITECTURE.md: Volume mount design
- RUNPOD_S3_ARCHITECTURE_DIAGRAM.txt: S3 API vs filesystem access
- DOCKERFILE_RUNPOD_FINAL_SUMMARY.md: Docker image specification

### Decision Documentation
- RUNPOD_DEPLOYMENT_CHECKLIST.md: Go/no-go decision matrix (27KB)
- RUNPOD_DEPLOYMENT_DECISION_TREE.md: Decision workflow
- FP32_RUNPOD_DEPLOYMENT_READY.md: FP32 deployment readiness

## QAT Enhancements

### Core QAT Infrastructure
- ml/src/memory_optimization/qat.rs: Enhanced QAT observer (+226 lines)
- ml/src/memory_optimization/auto_batch_size.rs: OOM recovery (+84 lines)
- ml/src/tft/qat_tft.rs: QAT TFT wrapper (+154 lines)
- ml/src/trainers/tft.rs: QAT training integration (+433 lines)
- ml/src/qat_metrics_exporter.rs: NEW - QAT metrics export

### QAT Testing
- ml/tests/qat_integration_tests.rs: NEW - Integration test suite
- ml/tests/qat_gradient_clipping_test.rs: NEW - Gradient clipping tests
- ml/tests/qat_device_consistency_test.rs: Device mismatch tests (+205 lines)
- ml/tests/qat_accuracy_validation_test.rs: Accuracy validation
- ml/tests/qat_tft_integration_test.rs: TFT QAT integration

### QAT Documentation
- ml/docs/QAT_GUIDE.md: Comprehensive QAT guide (+616 lines)
- ml/docs/QAT_GRADIENT_CHECKPOINTING_WORKAROUND.md: NEW - Workaround guide
- QAT_BLOCKERS_ROOT_CAUSE_ANALYSIS.md: P0 blocker analysis (44KB)
- QAT_ACCURACY_VALIDATION_REPORT.md: Accuracy comparison
- QAT_GRADIENT_CLIPPING_VALIDATION_REPORT.md: Clipping validation

### QAT Monitoring
- config/grafana/dashboards/qat-training-metrics.json: NEW - Grafana dashboard

## AWS CLI Configuration

### Credentials Setup
- ~/.aws/credentials: Runpod profile configured
  - Access Key: user_2xxA3XcIFj16yfL3aBon9niiSpr
  - Secret Key: (from RUNPOD_S3_SECRET)
- ~/.aws/config: Iceland region (eur-is-1)

## Production Readiness

### FP32 Models:  READY FOR DEPLOYMENT
- DQN: 15-20s training, ~6MB GPU memory
- PPO: 7-10s training, ~145MB GPU memory
- MAMBA-2: 2-3 min training, ~164MB GPU memory
- TFT-225: 3-5 min training, ~500MB GPU memory
- Total GPU Budget: 815MB (fits on 4GB+ Tesla V100)

### QAT Models: 🔴 BLOCKED
- 24 tests implemented but DO NOT COMPILE (11 errors)
- 3 P0 blockers: device mismatch, gradient checkpointing, OOM recovery
- Timeline: 1-2 weeks to fix (13h P0 fixes + validation)

### Wave D Features:  OPERATIONAL
- 225 features fully integrated
- Feature extraction: 5.10μs/bar (196x faster than target)
- Wave D backtest: Sharpe 2.00, Win Rate 60%, Drawdown 15%
- Database migration 045: Applied cleanly, zero conflicts

## Cost Analysis

### One-Time Setup
- Network Volume: $4/month (50GB SSD)
- Upload costs: FREE (S3 API included)

### Per Training Run (TFT-225)
- GPU: Tesla V100-PCIE-16GB @ $0.29/hr
- Training Time: ~4 hours
- Cost per run: $1.16

### Monthly (20 Training Runs)
- Storage: $4.00/month
- Training: $23.20/month (20 runs × $1.16)
- Total: $27.20/month

## Security

### Credentials Management
-  NO credentials in Docker image
-  NO credentials in Terraform state
-  .env gitignored and not committed
-  .env file private on S3 (HTTP 401 on public access)
-  Docker Hub repository PRIVATE (jgrusewski/foxhunt)

### Access Control
- S3 API: Local client uploads only
- Volume mount: Pod filesystem access only
- Authentication: AWS CLI with Runpod profile required

## Next Steps

1.  COMPLETE: Build Docker image
2.  PENDING: Push to Docker Hub
3.  PENDING: Deploy pod via Runpod console
4.  PENDING: Validate training on Tesla V100

## Performance Targets

- Build time: 5-10 min
- Upload time: ~20 sec (90MB total)
- Pod startup: ~30 sec
- Training time: 3-5 min (TFT-225)
- Total deployment: ~40 min from start to first training run

## Test Status

- FP32 tests: 597/608 passing (98.2%)
- QAT tests: 0/24 passing (compilation errors)
- Overall: 2,062/2,086 passing (98.8% excluding QAT)

🤖 Generated with Claude Code (https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-24 01:11:43 +02:00

300 lines
8.5 KiB
Rust

//! Machine learning configuration
use serde::{Deserialize, Serialize};
use std::collections::HashMap;
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct MLConfig {
pub model_config: ModelArchitectureConfig,
pub training_config: TrainingConfig,
pub simulation_config: SimulationConfig,
}
/// Configuration for market data simulation and stress testing
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct SimulationConfig {
/// Initial market state with configurable symbol prices
pub initial_market_state: MarketState,
/// Simulation parameters
pub parameters: SimulationParameters,
/// Test symbol configuration for generic testing
pub test_symbols: TestSymbolConfig,
}
/// Initial market state configuration
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct MarketState {
/// Symbol-specific initial prices and configuration
pub symbols: HashMap<String, SymbolConfig>,
/// Default configuration for unlisted symbols
pub default_symbol: SymbolConfig,
}
/// Configuration for individual symbols
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct SymbolConfig {
/// Initial price for the symbol
pub initial_price: f64,
/// Base volatility for the symbol
pub volatility: f64,
/// Base trading volume
pub base_volume: f64,
/// Minimum spread in basis points
pub min_spread_bps: f64,
/// Maximum spread in basis points
pub max_spread_bps: f64,
/// Market capitalization tier (affects behavior)
pub market_cap_tier: MarketCapTier,
}
/// Market capitalization tiers for different symbol behaviors
#[derive(Debug, Clone, Serialize, Deserialize)]
pub enum MarketCapTier {
/// Large cap stocks (>$10B)
LargeCap,
/// Mid cap stocks ($2B-$10B)
MidCap,
/// Small cap stocks (<$2B)
SmallCap,
/// Generic test symbol
Test,
}
/// Simulation parameters
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct SimulationParameters {
/// Update rate in Hz
pub update_rate_hz: u32,
/// Base market volatility
pub base_volatility: f64,
/// Market trend direction (-1.0 to 1.0)
pub trend: f64,
/// Enable realistic market microstructure
pub enable_microstructure: bool,
/// Enable correlated movements between symbols
pub enable_correlation: bool,
}
/// Test symbol configuration for generic testing
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TestSymbolConfig {
/// Prefix for test symbols (e.g., "TEST")
pub symbol_prefix: String,
/// Number of test symbols to generate
pub count: usize,
/// Price range for test symbols
pub price_range: (f64, f64),
/// Volume range for test symbols
pub volume_range: (f64, f64),
}
/// Default simulation configuration
impl Default for SimulationConfig {
fn default() -> Self {
let mut symbols = HashMap::new();
// Production-ready major symbols with realistic configurations
symbols.insert(
"AAPL".to_owned(),
SymbolConfig {
initial_price: 150.0,
volatility: 0.25,
base_volume: 50_000_000.0,
min_spread_bps: 1.0,
max_spread_bps: 5.0,
market_cap_tier: MarketCapTier::LargeCap,
},
);
symbols.insert(
"MSFT".to_owned(),
SymbolConfig {
initial_price: 300.0,
volatility: 0.22,
base_volume: 30_000_000.0,
min_spread_bps: 1.0,
max_spread_bps: 5.0,
market_cap_tier: MarketCapTier::LargeCap,
},
);
symbols.insert(
"GOOGL".to_owned(),
SymbolConfig {
initial_price: 2500.0,
volatility: 0.28,
base_volume: 20_000_000.0,
min_spread_bps: 2.0,
max_spread_bps: 8.0,
market_cap_tier: MarketCapTier::LargeCap,
},
);
symbols.insert(
"TSLA".to_owned(),
SymbolConfig {
initial_price: 800.0,
volatility: 0.45,
base_volume: 80_000_000.0,
min_spread_bps: 2.0,
max_spread_bps: 10.0,
market_cap_tier: MarketCapTier::LargeCap,
},
);
symbols.insert(
"AMZN".to_owned(),
SymbolConfig {
initial_price: 3200.0,
volatility: 0.30,
base_volume: 25_000_000.0,
min_spread_bps: 2.0,
max_spread_bps: 8.0,
market_cap_tier: MarketCapTier::LargeCap,
},
);
symbols.insert(
"NVDA".to_owned(),
SymbolConfig {
initial_price: 500.0,
volatility: 0.40,
base_volume: 40_000_000.0,
min_spread_bps: 2.0,
max_spread_bps: 8.0,
market_cap_tier: MarketCapTier::LargeCap,
},
);
Self {
initial_market_state: MarketState {
symbols,
default_symbol: SymbolConfig {
initial_price: 100.0,
volatility: 0.30,
base_volume: 1_000_000.0,
min_spread_bps: 5.0,
max_spread_bps: 20.0,
market_cap_tier: MarketCapTier::Test,
},
},
parameters: SimulationParameters {
update_rate_hz: 1000,
base_volatility: 0.02,
trend: 0.0,
enable_microstructure: true,
enable_correlation: false,
},
test_symbols: TestSymbolConfig {
symbol_prefix: "TEST".to_owned(),
count: 10,
price_range: (50.0, 500.0),
volume_range: (100_000.0, 10_000_000.0),
},
}
}
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ModelArchitectureConfig {
pub model_type: String,
pub hidden_dims: Vec<usize>,
pub dropout_rate: f64,
pub activation: String,
}
impl Default for ModelArchitectureConfig {
fn default() -> Self {
Self {
model_type: "transformer".to_owned(),
hidden_dims: vec![256, 128, 64],
dropout_rate: 0.1,
activation: "relu".to_owned(),
}
}
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct TrainingConfig {
pub batch_size: usize,
pub learning_rate: f64,
pub epochs: u32,
pub early_stopping_patience: u32,
}
impl Default for TrainingConfig {
fn default() -> Self {
Self {
batch_size: 32,
learning_rate: 0.001,
epochs: 100,
early_stopping_patience: 10,
}
}
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Mamba2Config {
pub d_model: usize,
pub d_state: usize,
pub d_conv: usize,
pub expand: usize,
pub dt_rank: Option<usize>,
pub dt_min: f64,
pub dt_max: f64,
pub dt_init: String,
pub dt_scale: f64,
pub dt_init_floor: f64,
pub conv_bias: bool,
pub bias: bool,
pub use_fast_path: bool,
pub layer_idx: Option<usize>,
pub device: Option<String>,
pub dtype: Option<String>,
pub d_head: usize,
pub num_heads: usize,
pub num_layers: usize,
pub target_latency_us: u64,
pub hardware_aware: bool,
pub use_ssd: bool,
pub use_selective_state: bool,
pub max_seq_len: usize,
pub batch_size: usize,
pub seq_len: usize,
pub dropout: f64,
}
impl Default for Mamba2Config {
fn default() -> Self {
Self {
d_model: 768,
d_state: 128,
d_conv: 4,
expand: 2,
dt_rank: None, // Auto-calculated as ceil(d_model / 16)
dt_min: 0.001,
dt_max: 0.1,
dt_init: "random".to_owned(),
dt_scale: 1.0,
dt_init_floor: 1e-4,
conv_bias: true,
bias: false,
use_fast_path: true,
layer_idx: None,
device: None,
dtype: None,
d_head: 32,
num_heads: 8,
num_layers: 4,
target_latency_us: 3,
hardware_aware: true,
use_ssd: true,
use_selective_state: true,
max_seq_len: 1024,
batch_size: 1,
seq_len: 256,
dropout: 0.0,
}
}
}