User Safety in Distributed Systems: Building Safe Services at Scale
Understanding and implementing user safety at scale: architecture patterns, failure-mode handling, and production-proven strategies for distributed systems.
Building a Pure-Python INT4 Transformer Weight Quantizer with Block-Wise Per-Channel Scaling
A practical guide to building a pure-Python INT4 quantizer for transformer weights, demonstrating real systems skills for your portfolio.
Optimizing NVIDIA CUDA Graphs for Sparse Matrix Multiplication on GPU Clusters
This post details the end-to-end optimization of CUDA Graphs for sparse matrix multiplication across GPU clusters, covering architecture, implementation patterns, and performance benchmarks.
Hands-On Build Guide: Sliding-Window Attention KV Cache with LRU Eviction
A hands‑on guide to implementing a sliding‑window attention KV cache with LRU eviction, complete with runnable Python code, benchmarks, and extension ideas for production use.
Pure-Python INT8 Weight Quantizer for Transformer Inference: A Hands-On Build Guide
Learn to implement a production‑ready INT8 quantizer with per‑channel scaling, test it on transformer weights, and extend it for real‑world deployment.