tvm

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

AutoKernel 是一个简单易用，低门槛的自动算子优化工具，提高深度学习算法部署效率。

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

Optimizing Mobile Deep Learning on ARM GPU with TVM

Open, Modular, Deep Learning Accelerator

convert torch module to tensorrt network or tvm function

Reimplement RetinaFace using PyTorch.

TVM stack: exploring the incredible explosion of deep-learning frameworks and how to bring them together

A home for the final text of all TVM RFCs.

Benchmark scripts for TVM

动手学习TVM核心原理教程

Large input size REAL-TIME Face Detector on Cpp. It can also support face verification using MobileFaceNet+Arcface with real-time inference. 480P Over 30FPS on CPU

(MERGED) Rust bindings for TVM runtime

This project contains a code generator that produces static C NN inference deployment code targeting tiny micro-controllers (TinyML) as replacement for other µTVM runtimes. This tools generates a runtime, which statically executes the compiled model. This reduces the overhead in terms of code size and execution time compared to having a dynamic on-device runtime.

ANT framework's model database that provides DNN models for the various range of IoT devices

TVM learning and research

DietCode Code Release

DEPRECATED: this repo has been moved into https://github.com/dmlc/tvm/blob/master/rust

Benchmarks for popular classification and object detection models on CPUs and GPUs

Canopy is a machine learning learning compiler stack with the capability of adopting high-end FPGAs. As a part of OpenAIOS project, Canopy is an evolved version of Apache TVM. Canopy is able to support a variety of hardware backends such as PCIE-based cloud FPGAs, CPUs and GPUs.

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

各类深度模型的优化器，包括tvm、tf-tensorrt、tensorrt等。