Hands-On System Programming with C++, published by Packt

Patterns and resources of low latency programming.

A curated list of resources on operating system design and implementation.

An implementation of the Raft distributed consensus protocol using the Tokio framework.

Accelerating MoE with IO and Tile-aware Optimizations

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Mamba SSM architecture

FlashInfer: Kernel Library for LLM Serving

Extract tables from PDF files

Algorithms for latent compaction

LLM KV cache compression made easy

Systems Programming UIUC FA 2016

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.

Fast and memory-efficient exact attention

A course to build the SQL layer of a distributed database.

A course to build distributed key-value service based on TiKV model

High-performance wait-free memory reclamation for wait-free data structures (ASMR). Bounded memory usage, predictable latency.

Raft distributed consensus algorithm implemented in Rust.

Implementation of Chandy–Lamport snapshot algorithm for recording a consistent global state of an asynchronous distributed system

Chandy-Lamport distributed snapshot implementation

My UCLA ECE M116C Fall 2022 Resources

A circular buffer written in C using Posix calls to create a contiguously mapped memory space. BSD Licensed.