Pinned Loading

1. triton-monitor triton-monitor Public

   Built a GPU inference monitoring and load testing system using NVIDIA Triton, GCP, Prometheus, and Grafana to analyze performance under concurrent workloads.

   Python

2. per_core_lock_free_event_bus per_core_lock_free_event_bus Public

   A high-performance C++ event bus utilizing a lock-free SPSC ring buffer with cache-line alignment to eliminate thread contention.

   C++

3. infra-drift-system infra-drift-system Public

   Forecasting and drift detection suite designed to maintain high-fidelity performance baselines across large-scale infrastructure clusters

4. h100-inference-control-plane h100-inference-control-plane Public

   Production-grade GPU Inference Platform built on H100 GPUs rented off RunPod

   Shell