interestingLSY

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"

hpcgame.minesweeper

DDL-Firewall

intServer

A high performance minecraft server, in C++20

MyBlog

NeuroFrame

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

24-2048

interestingLSY.github.io

My homepage

intoj-judger-rebuild

IntPool

mdx-net-submission

node-multi-hashing

node-stratum-pool

High performance Stratum poolserver in Node.js

NoobPool

NoobPool 菜鸟矿池

vllm

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

cherry-markdown

✨ A Markdown Editor

contrib-mlcommons-ck

Fork of the repo "mlcommons/ck" that add multi-node pytorch SUT's implementation

contrib-mlcommons-inference

Fork of the repo "mlcommons/inference" that implements multi-node pytorch SUT

cpuminer-opt

Optimized multi algo CPU miner

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

diff-gaussian-rasterization

gitignore

A collection of useful .gitignore templates

intclock

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

luogu-problem-list

A problem list for luogu OJ.

Pintos-gitbook

The gitbook for Pintos project in Peking University.

pyecm

Pyecm factors large integers (up to 50 digits) using the Elliptic Curve Method (ECM), a fast factoring algorithm.

pysinsy

Python wrapper for Sinsy

triton-hotfix