hlky's repositories
AITemplate
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
AAAIT
Additional Adventures with AITemplate
Language:PythonApache-2.0000
aitnpy
AITemplate🤝Numpy
Language:Python000
cutlass
CUDA Templates for Linear Algebra Subroutines
Language:C++NOASSERTION000
Language:Python000
Language:Python000
Language:PythonApache-2.0000
Language:RustApache-2.0000
huggingface_hub
The official Python client for the Huggingface Hub.
Apache-2.0000
Language:TypeScriptApache-2.0000
webdataset
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
BSD-3-Clause000