< Projects />

LIVE DEMO ACTIVE

Systems

LLM Admission Gateway — Reserve, Commit, Expire

A rate limiter for inference traffic, where cost is tokens rather than requests and the dominant part of that cost is u…

TypeScript Node.js Redis Lua +3

EXPLORE()

ACTIVE

Systems

Titans — A Nanosecond Fast Path with an LLM Slow Lane

An event-driven C++20 trading engine built around a hard boundary between a nanosecond fast path and an LLM-scale slow …

C++20 CMake Docker Prometheus +2

EXPLORE()

COMPLETED

Systems

JetsonProj — CUDA Hook Analyzer

A CUDA-level profiling and intelligent multi-model inference scheduling framework for edge AI, achieving 114.67 FPS YOL…

C++17 CUDA 12.6 TensorRT 10.3 CMake +8

EXPLORE()

COMPLETED

Systems

VecDB-WASM

Browser-native vector database in Rust compiled to WebAssembly — HNSW + Flat indices, SIMD128 acceleration for 7 distan…

Rust WebAssembly SIMD128 HNSW +2

EXPLORE()

LIVE DEMO COMPLETED

Systems

Mandelbrot-Renderer

Multi-paradigm fractal renderer spanning 5 compute backends (JS → WASM → CPU → OpenMP → CUDA) with 125,000x GPU speedup…

C++17 CUDA 12.6 OpenMP Emscripten +2

EXPLORE()

PRIVATE ACTIVE

Systems

AgentMesh

Distributed multi-agent coordination runtime with actor model, AST-based conflict detection, backpressure, and circuit …

Python Ray asyncio

EXPLORE()

PRIVATE COMPLETED

Systems

Infer-GC

GC-aware LLM inference engine applying garbage collection semantics (reference counting, generational collection, memor…

Python PyTorch CUDA PagedAttention +1

EXPLORE()

COMPLETED

Systems

Vulkan-Study

Interactive Vulkan learning system with 20 progressive exercises and a final renderer project

C++17 Vulkan 1.2+ GLFW GLM +2

EXPLORE()

PRIVATE COMPLETED

Systems

s3-like-storage

An S3-compatible distributed object store with a purpose-built LLM KV-cache engine: radix tree keyed on token prefixes,…

Go 1.21+ PostgreSQL Redis Nginx +2

EXPLORE()