yzh119

bibfetch

Fetch bibtex entries from academic search engines like dblp.

mirage

A multi-level tensor algebra superoptimizer

punica

Serving multiple LoRA finetuned LLM as one

mlc-llm

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

relax

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

dgsparse

envd

🏕️ Reproducible development environment for AI/ML

flashinfer-ai.github.io

Project website of FlashInfer project

graphiler

llm-perf-bench

Magicube

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

metal-benchmarks

Apple GPU microarchitecture

mlx

MLX: An array framework for Apple silicon

mogan

Mogan Editor / 墨干编辑器

nccl

Optimized primitives for collective multi-GPU communication

nnfusion

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

relax-sparse

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

sam

smoothquant

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

sputnik

A library of GPU kernels for sparse matrix operations.

taco

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

tlcpack

triton

Development repository for the Triton language and compiler

tvm

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

tvm-rfcs

A home for the final text of all TVM RFCs.

utils

uwsampl.github.io

The UW SAMPL group's website.

web-data

web-llm

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

web-stable-diffusion

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