uncomplicate/deep-diamond

A fast Clojure Tensor & Deep Learning library

What it solves

Deep Diamond is designed to provide Clojure developers with a way to perform fast tensor operations and neural network computations without sacrificing performance, by leveraging highly optimized native libraries for both CPU and GPU execution.

How it works

The library acts as a wrapper or interface to native computation routines. It provides different backend options to support various hardware, including specific implementations for CUDA (GPU) and DNNL (CPU), as well as BNNS (Apple's Basic Neural Network Subroutines).

Who it’s for

It is intended for Clojure programmers who need to build neural networks or perform heavy numerical tensor computations on their local hardware.

Highlights

  • Fast tensor and neural network computations.
  • Support for both CPU and GPU acceleration.
  • Multiple backend options including CUDA, DNNL, and BNNS.

Related

  • Project
    uncomplicate/neanderthal

    Neanderthal is a Clojure library for high-performance matrix and linear algebra computations utilizing optimized native BLAS and LAPACK routines on CPU and GPU.

  • Project
    techascent/tech.ml.dataset

    A Clojure library for high-performance tabular data processing on the JVM, providing a functional alternative to Pandas or R's data.table.

  • Project
    deepseek-ai/DeepGEMM

    A high-performance tensor core kernel library for NVIDIA GPUs that provides optimized GEMM, MoE, and MQA kernels to accelerate LLM training and inference.

  • Project
    NVIDIA/CUDALibrarySamples

    A collection of GPU-accelerated examples demonstrating the use of NVIDIA CUDA libraries for high-performance math, image processing, and linear algebra.

  • Project
    NVIDIA/TensorRT

    NVIDIA TensorRT is a high-performance deep learning inference library and SDK that accelerates AI model deployment on NVIDIA GPUs.