Zihao Ye

Open deep learning compiler stack for cpu, gpu and specialized accelerators

TVM FFI

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"

Code for SegTree Transformer (ICLR-RLGM 2019).

To do experiments on language grounding.

Evaluate the chunking performance on CONLL-2000 dataset

Fetch bibtex entries from academic search engines like dblp.

naive graph attention kernels

Homework of CS225(Instructor: Yitong Yin)

A multi-level tensor algebra superoptimizer

Serving multiple LoRA finetuned LLM as one

No description.

A naive compiler from Mx* to MIPS

[WIP]Switch the backend of dgl to tvm.

No description.

No description.

Must-have verilog systemverilog modules

My automation library

(Spring 2018) Assignment 2: Graph Executor with TVM

No description.

An open-source NLP research library, built on PyTorch.

No description.

No description.

The source code for "An Actor Critic Algorithm for Structured Prediction"

No description.

Course assignment of CS230.

No description.

Benchmark different ffi solutions

No description.

Raft distributed consensus algorithm implemented in Rust.

No description.

Course homework of CS389.

Experiments on Transfer Learning

Machine-learning models for VCMI (Heroes of Might and Magic III).

FlashInfer: Kernel Library for LLM Serving

No description.

Ongoing research training transformer models at scale

A fast communication-overlapping library for tensor/expert parallelism on GPUs.

No description.

Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.

No description.

Efficient, Flexible and Portable Structured Generation

Official NetHack Git Repository

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

Source code to pbrt, the ray tracer described in the forthcoming 4th edition of the "Physically Based Rendering: From Theory to Implementation" book.

NVIDIA Linux open GPU kernel module source

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

No description.

mirror of GNU Guile

Source Code of GNU TeXmacs, Developers Guide ==>

Development repository for the Triton language and compiler

MLX: An array framework for Apple silicon

Apple GPU microarchitecture

Optimized primitives for collective multi-GPU communication

Project website of FlashInfer project

Intermediate Language (IL) for Hardware Accelerator Generators

No description.

No description.

No description.

Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

A home for the final text of all TVM RFCs.

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

No description.

Temp repo for prototyping relax(relay next), the effort will be upstreamed. We use the wiki pages on this repo to host design docs.

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

🏕️ Reproducible development environment for AI/ML

No description.

Mogan Editor / 墨干编辑器

A library of GPU kernels for sparse matrix operations.

Prune a model while finetuning or training.

A Linux-capable RISC-V multicore for and by the world

[MLSys'22] TorchSparse: Efficient Point Cloud Inference Engine

No description.

No description.

A list of tutorials, paper, talks, and open-source projects for emerging compiler and architecture

Defragmentation during migragation in HeMem (CSE599f Sp 2022)

A library for syntactically rewriting Python programs, pronounced (sinner).

No description.

Distributed Systems Labs and Framework

Tutel MoE: An Optimized Mixture-of-Experts Implementation

This package contains deep learning models and related scripts for RoseTTAFold

The UW SAMPL group's website.

CUDA Templates for Linear Algebra Subroutines

No description.

Benchmark scripts for TVM

Additional sphinx theming on top of rtd theme with support for header and footer

Long Range Arena for Benchmarking Efficient Transformers

Color palettes for gnuplot

No description.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

egg is a flexible, high-performance e-graph library

Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies.

No description.

A simple but usable RPC framework

[EXPERIMENTAL] Tools for the concurrent manipulation of variably sized Tensors.

Benchmark datasets, data loaders, and evaluators for graph machine learning

personal vim settings for c/cpp project

RFC for common in-memory tensor structure and operator interface for deep learning system

Productive & portable programming language for high-performance, sparse & differentiable computing

Light-weight GPU kernel interface for graph operations

Chisel examples and code snippets

example LLVM pass

Cross-platform vectorization of Julia code using Accelerate, VML, and Yeppp!

A system for quickly generating training data with weak supervision

Official MINIX sources - Automatically replicated from gerrit.minix3.org

Relax! Flux is the ML library that doesn't make you tensor

Beautiful pseudocode for the Web

No description.

No description.

SSA vs ANF

A distributed graph deep learning framework.

Research language for array processing in the Haskell/ML family

An Open Source Machine Learning Framework for Everyone

Data loaders and abstractions for text and NLP

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs

Code for the paper "Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks"

No description.

Word embedding approach based on a dynamic log-linear model

NLP made easy

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

baseline

No description.

Proof of concept for a dynamic named tensor for pytorch

Shor algorithm in Q#

Extensible, Efficient Quantum Algorithm Design for Humans.

Mixed Incremental Cross-Entropy REINFORCE ICLR 2016

Experiment Code for Paper ``CoT: Cooperative Training for Generative Modeling''

Subword Neural Machine Translation

PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"

Open Source Neural Machine Translation in PyTorch

A lightweight parameter server interface

A XeLaTeX template for Shanghai Jiao Tong University (SJTU) thesis.

A python tool for evaluating the quality of sentence embeddings.

Sentence embeddings (InferSent) and training code for NLI.

Tensorflow implementation of "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"

Repository for "Generating Sentences by Editing Prototypes"

GloVe model for distributed word representation

No description.

Assignment 2: GPU Executor

To implement a WGAN on MNIST dataset.

No description.

No description.

Assignment 1: automatic differentiation

No description.

The final project of Computer System

An Airbnb-like system.(Course Project A of CS392: Database Systems)

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Course assignment of CS389(Instructor: John Hopcroft)

Tutorial code on how to build your own Deep Learning System in 2k Lines

DeepLearning Course Assignments

Scientific Computation Library

An interpreter for Scheme.

transform markdown file to html

An easy static website generator.