Gradually-Warmup Learning Rate Scheduler for PyTorch
-
Updated
Oct 10, 2024 - Python
Gradually-Warmup Learning Rate Scheduler for PyTorch
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)
Polynomial Learning Rate Decay Scheduler for PyTorch
A pyTorch Extension for Applied Mathematics
Faster Pytorch bitsandbytes 4bit fp4 nn.Linear ops
Pytorch extension for openml-python
Template for CUDA / C++ extension writing with PyTorch
XNOR-Net with binary conv2d kernels with XNOR GEMM op, support both CPU and GPU.
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Binding C++ to PyTorch and extending PyTorch
CUDA kernels for LLM inference: FlashAttention forward, Tensor Core GEMM, PyTorch bindings, and benchmarkable reference implementations.
The numerical continuity layer for GPU computing
PyTorch extension for alternative backward rules and gradient transforms (STE, gradient jamming, non-standard activations).
simple examples of tools and libraries
High-performance matrix engine for Unit-Domain Flow (UDF). Eliminates Mantissa Friction with 0.00 MSE integrity.
Add a description, image, and links to the pytorch-extension topic page so that developers can more easily learn about it.
To associate your repository with the pytorch-extension topic, visit your repo's landing page and select "manage topics."