zineos

tflite-micro

TensorFlow Lite for Microcontrollers

bitsandbytes

8-bit CUDA functions for PyTorch

blue-porcelain

bragghls

PyTorch model to RTL flow for low latency inference

codon

A high-performance, zero-overhead, extensible Python compiler using LLVM

composable_kernel

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

cpython

The Python programming language

crack_leetcode

五天刷题，三天模拟！快速掌握leetcode解题套路！

CUDA-Programming

Sample codes for my CUDA programming book

EtinyNet

firesim-nvdla

FireSim-NVDLA: NVIDIA Deep Learning Accelerator (NVDLA) Integrated with RISC-V Rocket Chip SoC Running on the Amazon FPGA Cloud

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers"

GPTQ-for-LLaMa

4 bits quantization of LLaMa using GPTQ

hidet

An open-source efficient deep learning framework.

how-to-optim-algorithm-in-cuda

how to optimize some algorithm in cuda.

ITRI-OpenDLA

OpenDLA for trying the demo and FPGA solution

lc3-vm

Write your own virtual machine for the LC-3 computer!

llama-int8

Quantized inference code for LLaMA models

llama.cpp

Port of Facebook's LLaMA model in C/C++

llama.onnx

llama onnx models and onnxruntime demo

MegFlow

Efficient ML solution for long-tailed demands.

mlir-emitc

Conversions to MLIR EmitC

nncg

NNCG: A Neural Network Code Generator

nnfusion

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

qlib

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. An increasing number of SOTA Quant research works/papers are released in Qlib.

relay-bench

A repository containing examples and benchmarks for Relay.

relay-mlir

An MLIR-based toy DL compiler for TVM Relay.

stable-diffusion

tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; MCUNetV3: On-Device Training Under 256KB Memory

WaifuXL

State of the art image upscaling, directly in your browser.