gorazd 0.3.0

Institutional quantitative execution and physical reality matrix.

GORAZD: Institutional UHFT Execution Matrix

Gorazd is an ultra-high-frequency, zero-allocation quantitative execution engine designed for bare-metal Linux deployments. It physically bypasses the Python Global Interpreter Lock (GIL) and OS-level mutexes to achieve deterministic microsecond execution.

Architectural Supremacy

• Zero-Allocation Memory: Pre-allocated monolithic C-tensors (StaticMemoryPool).
• Lock-Free IPC: Inter-Process Communication using C11 atomic pointers and 64-byte L1 cache-line padding (SPSCRingBuffer).
• Native C-API Inference: Bypasses Python wrappers, mapping RAM directly to libxgboost.so via ctypes.
• Stateful Friction Physics: Custom XGBoost objective gradients mathematically constrained by real-time bid-ask transaction costs.
• Fractional Kelly Sizing & TWAP: Dynamic capital exposure scaled by inverse volatility and sliced via Limit Order book concealment.
• Kernel Bypass Ready: Architected to map directly to Solarflare/Mellanox DPDK ring buffers.

Deployment Profile

Designed strictly for isolated CPU cores (isolcpus) on Equinix NY4 bare-metal infrastructure.

Version 0.2.0 - Asynchronous Ingress & Telemetry Overhaul.