Lianmin Zheng

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

Training and serving large-scale neural networks

End to end Tensor IR/DSL stack for deploying deep learning workloads to hardwares

A list of awesome compiler projects and papers for tensor computation and deep learning.

Optimizing Mobile Deep Learning on ARM GPU with TVM

A simple implementation of the Google File System in golang

A compiler for the course Compiler 2017 at ACM Class, SJTU.

Implementation of Neural Arithmetic Logic Units (https://arxiv.org/pdf/1808.00508.pdf)

A curated list for Efficient Large Language Models

No description.

Werewolf, a board game

A C-minus compiler runs on the CASIO FX-9860 graphing calculator

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

An effective tool to help you to review new words.

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

a language for fast, portable data-parallel computation

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An Open Source Machine Learning Framework for Everyone

PyTorch native quantization and sparsity for training and inference

No description.

A distributed deep learning framework that supports flexible parallelization strategies.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A common bricks library for building scalable and portable distributed machine learning.

Symbolic Expression and Statement Module for new DSLs

Dynamic Tensor Rematerialization prototype (modified PyTorch) and simulator. Paper: https://arxiv.org/abs/2006.09616

testcase for PPCA 2017 deep learning system

WeFlow - 一个本地的微信聊天记录导出和年度报告应用

personal website

chat log tool, easily use your own chat data. 聊天记录工具，轻松使用自己的聊天数据

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Structured Text Generation

FlashInfer: Kernel Library for LLM Serving

Code for the paper "Evaluating Large Language Models Trained on Code"

SGLang is yet another fast serving framework for large language models and vision language models.

Stanford DSPy: The framework for programming—not prompting—foundation models

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

A Framework for Model-Backed Generators. Backend for AutoPandas (https://autopandas.io)

gnark-crypto provides elliptic curve and pairing-based cryptography on BN, BLS12, BLS24 and BW6 curves. It also provides various algorithms (algebra, crypto) of particular interest to zero knowledge proof systems.

Config files for my GitHub profile.

This repository contains integer operators on GPUs for PyTorch.

Tutorial for writing constraints in the `arkworks` framework

Mesh TensorFlow: Model Parallelism Made Easier

Backprop with Low-Precision Activations

MONeT framework for reducing memory consumption of DNN training

A numerical computing library for python that scales.

Some microbenchmarks and design docs before commencement

The UW SAML group's website.

A Simple & Flexible Cross Framework Operators Toolkit

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Bring deep learning to bare metal

A domain specific language to express machine learning workloads.

An interactive book on deep learning. Much easy, so MXNet. Wow.