Popular GitHub Repositories for Tvm

Universal LLM Deployment Engine with ML Compilation

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

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

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。

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

?? Chat with LLM like Vicuna totally in your browser with WebGPU, safely, privately, and with no server. Powered by web llm.

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

??? This repository lists some awesome public CUDA, cuda-python, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR, PTX and High Performance Computing (HPC) projects.

A curated list of awesome inference deployment framework of artificial intelligence (AI) models. OpenVINO, TensorRT, MediaPipe, TensorFlow Lite, TensorFlow Serving, ONNX Runtime, LibTorch, NCNN, TNN, MNN, TVM, MACE, Paddle Lite, MegEngine Lite, OpenPPL, Bolt, ExecuTorch.

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

Machine Learning Compiler Road Map

LCAI-TIHU SW is a software stack of the AI inference processor based on RISC-V

? AI CRYPTO STARTUP | Open Source ? AI ? Crypto ? DeFi ? TON ? Join our ambitious community as we merge AI, Crypto, and DeFi on TON! We’re collaboratively building courses, growing our startup, and rewarding contributors with NFT-based profits. Be part of the next-gen revolution — jump in, share ideas, and let’s shape the future together! ??

Post quantization with TensorFlow and model compilation with TVM

Generate batches of images in your browser with Stable Diffusion - private, free, and no installation required.

deep learning inference perf analysis

Comparing different quantization schemes in terms of inference speed for ResNet50.

A flow to compile ESPCN (super resolution) using TVM and run the compiled model on CPU to calculate PSNR

A flow to compile YOLOv3/SSD using TVM and run the compiled model on CPU to calculate mAP