mistaro

ColossalAI

Making large AI models cheaper, faster and more accessible

mlc-llm

Universal LLM Deployment Engine with ML Compilation

DALI

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

iree

A retargetable MLIR-based machine learning compiler and runtime toolkit.

awesome-tensor-compilers

A list of awesome compiler projects and papers for tensor computation and deep learning.

awesome-model-quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

armnn

Arm NN ML Software. The code here is a read-only mirror of https://review.mlplatform.org/admin/repos/ml/armnn

pytorch-auto-drive

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help

onnc

Open Neural Network Compiler

orion

An interference-aware scheduler for fine-grained GPU sharing

tzer

Tzer: TVM Implementation of "Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation (OOPSLA'22)“.

microflow-rs

A robust and efficient TinyML inference engine.

Elysium

[ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM

ObjectCompose

About Official repository of paper titled "ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes"

RLMC

tfopgen

Generate C++ and CUDA boilerplate for tensorflow custom operators

CUDAsmith

A CUDA compiler fuzzer

iron

Image Registration on FPGAs

tlm

cacheflow

CacheFlow is a Linux kernel module that exposes the contents of the last-level cache on *most* ARM machines.

uni-henn

mlir-generator

Generator for MLIR files from known front-ends

starlight

Starlight: A Kernel Optimizer for GPU Processing

TileGraph

:construction:WIP:construction: TileGraph is an experimental DNN compiler that utilizes static code generation and kernel fusion techniques.

DRL-DroneNavigation

Deep Reinforcement Learning for Autonomous Drone Navigation

fantastic_weights_paper

Repository for the paper: "Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training"

req_sat

Replication Package for Requirements Satisfiability with In-Context Learning

TGGLinesPlus

Jupyter notebooks for TGGLinesPlus computer vision algorithm for line detection from images

nspl

Official repository for NSPL: Neuro-Symbolic Preference Learner from human demonstrations

NBIoT_NPRACH_UAD

NPRACH UAD Neural Network implementation in Fixed point C.