Pinned Repositories
caffe
Ristretto: Caffe-based approximation of convolutional neural networks.
CuAssembler
An unofficial cuda assembler, for all generations of SASS, hopefully ：）
cutlass
CUDA Templates for Linear Algebra Subroutines
kernl
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
rocMLIR
keilsmart's Repositories
keilsmart/caffe
Ristretto: Caffe-based approximation of convolutional neural networks.
keilsmart/CuAssembler
An unofficial cuda assembler, for all generations of SASS, hopefully ：）
keilsmart/cutlass
CUDA Templates for Linear Algebra Subroutines
keilsmart/kernl
Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.
keilsmart/llvm-project
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
keilsmart/onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
keilsmart/oneflow
OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.
keilsmart/openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
keilsmart/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keilsmart/rocMLIR
keilsmart/stable-fast
Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
keilsmart/Stochastic-Quantization
Training Low-bits DNNs with Stochastic Quantization
keilsmart/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
keilsmart/web-stable-diffusion
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
keilsmart/YOLOv3-model-pruning
对 YOLOv3 做模型剪枝，在 oxford hand 数据集上模型的参数量减少 80% ，FLOPs 降低 70%，Infer 的速度可以达到原来的 200%，mAP 基本保持不变