Systems

A block‑sparse attention matrix visualized as a grid of active blocks.

Building a Pure‑Python Block‑Sparse Sliding‑Window Attention (Longformer‑Style)

Implement block‑sparse sliding‑window attention in pure Python to handle long sequences efficiently, mirroring Longformer’s design.

Illustration of goroutines flowing across processor queues in a Go service

Goroutine Scheduling in Go: Inside the Runtime That Powers Production Services

Understanding Go’s scheduler is essential for writing low‑latency, high‑throughput services. This article walks through the GMP model, context switching, and real‑world tuning levers.

Python code on a laptop screen next to a diagram of memory blocks

Hands-On Build Guide: Paged Attention KV Cache Manager with Block Allocation and Prefix Caching in Python

A step‑by‑step guide to implementing a paged attention KV cache in Python, perfect for CV demonstration.

A schematic of multiple LoRA adapters connected to a shared base model.

Multi-Adapter LoRA Inference Engine with Weight Paging and Shared Base

A hands‑on guide to building a multi‑adapter LoRA inference engine with weight paging and a shared base model, perfect for showcasing systems engineering skills.

A diagram of paged attention memory layout

From Scratch: Building a Paged Attention KV Cache for Transformer Inference

A practical build guide for a paged attention KV cache in pure Python, with architecture, code, and extensions for senior-level skills.