Shengyu Liu

swiftLLM. A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).

CUDA-From-Correctness-To-Performance-Code. Codes & examples for "CUDA - From Correctness to Performance"

hpcgame2026.kernel-design-trial. Python

hpcgame.minesweeper. C++

sysy-compiler. A compiler for the SYSY language (a subset of C). My homework for the course "compiler principles"

intOJ. A Online Judge System For The ACM-ICPC/OI Contest

NeuroFrame. A tiny framework for AI training and inference. My homework for the course "programming in AI".

DDL-Firewall. C++

intServer. A high performance minecraft server, in C++20

MyBlog. JavaScript

interestingLSY.github.io. My homepage

UCB-GPA-Calculator. 帮你计算 UCB 申请系统中的各种 GPA

FlashMLA. FlashMLA: Efficient MLA decoding kernels

node-stratum-pool. High performance Stratum poolserver in Node.js

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

node-multi-hashing. C

IntPool. JavaScript

NoobPool. NoobPool 菜鸟矿池

intoj-judger-rebuild. Python

24-2048. HTML