天津大学视觉形象识别系统 Visual Identity System of Tianjin University

IP质量检测脚本 - IP Quality Check Script

A Library Operating System for Serverless Workflow Applications.

Extending eBPF Programmability and Observability to GPUs (merged into https://github.com/eunomia-bpf/bpftime)

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

Material for gpu-mode lectures

SGLang is a high-performance serving framework for large language models and multimodal models.

My learning notes for ML SYS.

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

for paper @ ASPLOS‘25’

A refreshing and graceful Typora theme, like a gentle spring breeze.一款令人如沐春风的 Typora 灵动主题。

Linux kernel source tree

计算机自学指南

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Modeling, training, eval, and inference code for OLMo

Skin changer for League of Legends (LOL)

A DSL for Systolic Arrays

llama3 implementation one matrix multiplication at a time

Inference Llama 2 in one file of pure C

LLM training in simple, raw C/CUDA

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

[TMLR 2024] Efficient Large Language Models: A Survey

Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

A list of Free Software network services and web applications which can be hosted on your own servers

Master the command line, in one page

A PyTorch implementation of the Transformer model in "Attention is All You Need".

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