masahi

torchscript-to-tvm

tvm-cutlass-eval

libflash_attn

cutlass_fpA_intB_gemm

tensorir-experiment

tf2-detection-to-tvm

tvm

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

iwsec21_ntt

hb_tvm_example

models

Models and examples built with TensorFlow

ocaml_practice

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

pytorch_quantization

Test scripts for exploring PyTorch JIT and quantization capability

ci

Repository which handles configuration of TVM CI infrastructure.

cutlass

CUDA Templates for Linear Algebra Subroutines

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Halide

a language for fast, portable data-parallel computation

hummingbird

Hummingbird compiles trained ML models into tensor computation for faster inference.

hummingbird_test

int8_experiment

llmperf

LLMPerf is a library for validating and benchmarking LLMs

mlc-llm

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

nttverify

Artifact for FLOPS 2022 paper

openmoonray

MoonRay is DreamWorks’ open-source, award-winning, state-of-the-art production MCRT renderer.

relax

Temp repo for prototyping relax(relay next), the effort will be upstreamed. We use the wiki pages on this repo to host design docs.

taichi

Productive programming language for portable, high-performance, sparse & differentiable computing

TLCBench

Benchmark scripts for TVM

tvm-rfcs

A home for the final text of all TVM RFCs.

vision

Datasets, Transforms and Models specific to Computer Vision

web-stable-diffusion

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