bertmaher

llama2.so

Inference Llama 2 with a model compiled to native code by TorchInductor

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

tf32_gemm

Example of binding a TF32 CUTLASS GEMM kernel to PyTorch

bitserial

Hacking around with ultra-low precision GEMM using TVM

membench

deepstream-video-pipeline

pyhpc-benchmarks

A suite of benchmarks for CPU and GPU performance of the most popular high-performance libraries for Python :rocket:

ai_on_threads

Background-Matting

Background Matting: The World is Your Green Screen

benchmark

BERT-pytorch

Google AI 2018 BERT pytorch implementation

bertmaher.github.io

My GitHub site

builder

Continuous builder and binary build scripts for pytorch

cs344

ds2

Debug server for lldb.

fastNLP

fastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.

functorch

functorch is a prototype of JAX-like composable function transforms for PyTorch.

glow

Compiler for Neural Network hardware accelerators

hub

Submission to https://pytorch.org/hub/

learn_cuda

Simple programs for learning CUDA

lmdave

Let's Make: Dangerous Dave

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

midwit-matmul

A simplistic approach to high-performance GPU matmul

multipy

torch::deploy (multipy for non-torch uses) is a system that lets you get around the GIL problem by running multiple Python interpreters in a single C++ process.

nvprof2json

Convert nvprof profiles into about:tracing compatible JSON files

resume

The LaTeX sources for my resume/CV

torchdynamo

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

triton

Development repository for the Triton language and compiler

tvm

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

tvm-1

TVM integration into PyTorch