roastduck

FreeTensor

A language and compiler for irregular tensor programs.

YAUJ

Yet Another Universal Judge

vfk_uoj_sandbox

vfk's sandbox for uoj

FreeTensor_experiments

Experiments on FreeTensor

sfs

ADBench

Benchmarking various AD tools.

vllm

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

async-syscall-app

Userspace for roastduck/linux:async. Working in progress.

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

benchmark

A microbenchmark support library

capsule

Capsule network implemented with TVM

carbox2d

Simulator car evolution like http://boxcar2d.com

checkout

Action for checking out a repo

cutlass

CUDA Templates for Linear Algebra Subroutines

EETQ

Easy and Efficient Quantization for Transformers

Enzyme

High-performance automatic differentiation of LLVM and MLIR.

fastmoe

A fast MoE impl for PyTorch

googletest

GoogleTest - Google Testing and Mocking Framework

incubator-tvm

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

linux

Linux kernel source tree

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

longformer

Longformer: The Long-Document Transformer

onnx

Open standard for machine learning interoperability

pybind11

Seamless operability between C++11 and Python

pytorch-benchmark

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

rfs

A simple FS as a practice of Rust

spdlog

Fast C++ logging library.

taco

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

taskflow

A General-purpose Task-parallel Programming System using Modern C++

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.