masahi

torchscript-to-tvm. Cuda

nnvm-vision-demo. Demos interesting image-in, image-out networks running on both NVIDIA and AMD GPUs, with NNVM

tvm-cutlass-eval. Python

tvm-winograd. Test winograd convolution written in TVM for CUDA and AMDGPU

libflash_attn. C++

tf2-detection-to-tvm. Python

mxnet-cpp-inference. Test MXNet C++ API for doing inference, given a trained model

cutlass_fpA_intB_gemm. C++

tensorir-experiment. Python

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

autotvm-test. Benchmark AutoTVM against cuDNN and MIOpen

depth_estimation. Learning to predict depth from single image

iwsec21_ntt. Assembly

hb_tvm_example. Python

pytorch_quantization. Test scripts for exploring PyTorch JIT and quantization capability

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.

models. Models and examples built with TensorFlow

ocaml_practice. OCaml

mos. Multi organ segmentation, undergrad course project