Kv-Cache

Build a Minimal Transformer Inference Engine for Your Portfolio

A practical guide to building a minimal transformer inference engine with KV cache, tokenizer, attention, and sampler. It demonstrates systems skills that hiring managers look for.

Building a Paged KV Cache Allocator with Continuous Batching in Pure Python

This project demonstrates memory management, concurrent request scheduling, and low-level allocator design—all core skills for backend and ML infrastructure roles.

A visualization of paged attention memory blocks arranged in a cache hierarchy with eviction pointers

Build a Paged Attention KV-Cache Manager with LRU Eviction in Pure Python

A hands-on build guide for a paged attention KV-cache manager with LRU eviction in pure Python — a portfolio project that demonstrates LLM inference systems knowledge and signals senior-level engineering capability.

A conceptual diagram of paged KV cache blocks being allocated and managed in memory

Build a Paged KV Cache in Pure Python: A Portfolio Project That Signals Real Systems Skill

A hands-on guide to building a pure Python paged KV cache for transformer inference. This project demonstrates virtual-memory management, systems architecture, and deep learning engineering — exactly the skills hiring managers look for.

A visualization of paged KV cache memory blocks being swapped between CPU and GPU memory

Build a Paged KV Cache with Swapping for CPU-Only LLM Inference

A hands-on guide to building a paged KV cache with swapping for CPU-only LLM inference. Includes real, runnable Python code using PyTorch and demonstrates memory management patterns that signal senior-level systems skill.