Technical Writing 32
- How Profitable is LLM Inference? Doing the Math on Kimi K3
- Distributed LLM Inference with llm-d
- Exploring Speculative Decoding: From Concept to Implementation
- Exploring Mixture of Experts: From Concept to Inference Engine
- Deep Dive into Efficient LLM Inference with nano-vLLM
- Coding Agent with Self-hosted LLM: End-to-End Control with Opencode and vLLM
- MonClaw: A Minimal OpenClaw Built with the OpenCode SDK
- Taking a Look at OpenClaw (Clawdbot)
- Exploring UCP: Google's Universal Commerce Protocol
- Building A Coding Agent (Provider-agnostic)
- Notes on Distributed Consensus and Raft
- Exploring Kafka Cruise Control
- Is MCP Worth the Hype?
- Exploring Prometheus Internals: TSDB and XOR Encoding
- It's Not Always DNS: Exploring How Name Resolution Works
- The Internet is Cool. Thank you, TCP
- Inside Multi-Platform Docker Builds with QEMU
- A Practical Tour From Source to CPU
- Reducing Context Bloat with Dynamic Context Loading (DCL) for LLMs & MCP
- Exploring the Agentic Commerce Protocol (ACP)
- Exploring Terminals, TTYs, and PTYs
- How Coding Agents Actually Work: Inside OpenCode
- Is MCP a Security Nightmare?: A look into MCP Authorization with OAuth2
- Exploring Kafka Streams Internals
- Taking a Look at Database Disk, Memory, and Concurrency Management
- Meta MCP: Chaining Tools via Prompt-Driven Arguments
- Behind Sending Millions of Messages Per Second: A Look Under the Hood of Kafka Producer
- Gossip and Consensus: Using Serf and Raft to Build a Kafka-esque System
- How Are Images REALLY Stored?
- Taking a Look at Compression Algorithms
- MonKafka: Building a Kafka Broker from Scratch
- Exploring Apache Kafka Internals and Codebase