Search Results for "tensor"

ggml is an open-source tensor library designed for efficient machine learning computation with a focus on running models locally and with minimal dependencies. Written primarily in C and C++, the library provides low-level tensor operations and automatic differentiation that allow developers to implement machine learning algorithms and neural networks efficiently.

...To support a wide variety of applications, CUTLASS provides extensive support for mixed-precision computations, providing specialized data-movement and multiply-accumulate abstractions for half-precision floating point (FP16), BFloat16 (BF16), Tensor Float 32 (TF32), etc.

...Available across all common operating systems (desktop, server and mobile), TensorFlow provides stable APIs for Python and C as well as APIs that are not guaranteed to be backwards compatible or are 3rd party for a variety of other languages. The platform can be easily deployed on multiple CPUs, GPUs and Google's proprietary chip, the tensor processing unit (TPU). TensorFlow expresses its computations as dataflow graphs, with each node in the graph representing an operation. Nodes take tensors—multidimensional arrays—as input and produce tensors as output. The framework allows for these algorithms to be run in C++ for better performance, while the multiple levels of APIs let the user determine how high or low they wish the level of abstraction to be in the models produced. ...

...TensorRT is built on CUDA®, NVIDIA’s parallel programming model, and enables you to optimize inference leveraging libraries, development tools, and technologies in CUDA-X™ for artificial intelligence, autonomous machines, high-performance computing, and graphics. With new NVIDIA Ampere Architecture GPUs, TensorRT also leverages sparse tensor cores providing an additional performance boost.

Flashlight is a fast, flexible machine learning library written entirely in C++ by Facebook AI Research and the creators of Torch, TensorFlow, Eigen, and Deep Speech. Native support in C++ and simple extensibility make Flashlight a powerful research framework that's hackable to its core and enables fast iteration on new experimental setups and algorithms with little unopinionated and without sacrificing performance. In a single repository, Flashlight provides apps for research across...

Tensor Comprehensions (TC) is a fully functional C++ library that automatically synthesizes high-performance machine learning kernels using Halide, ISL, and NVRTC or LLVM. TC additionally provides basic integration with Caffe2 and PyTorch. We provide more details in our paper on arXiv. This library is designed to be highly portable, machine-learning-framework agnostic and only requires a simple tensor library with memory allocation, offloading, and synchronization capabilities.

...Infrastructure to automatically generates and optimize models on more backend with better performance. Compilation and minimal runtimes commonly unlock ML workloads on existing hardware. Automatically generate and optimize tensor operators on more backends. Need support for block sparsity, quantization (1,2,4,8 bit integers, posit), random forests/classical ML, memory planning, MISRA-C compatibility, Python prototyping or all of the above? NNVM flexible design enables all of these things and more.