6 repository-uri
Frameworks for distributed and parallel processing.
Explore 6 awesome GitHub repositories matching part of an awesome list · Parallel Computing. Refine with filters or upvote what's useful.
Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and layers using gradient-based and perturbation-based methods. It provides a modular framework for implementing, evaluating, and combining a range of explanation techniques, including gradient-based attribution, perturbation-based analysis, game-theoretic Shapley value approximation, and surrogate model explanations, with support for parallelization and noise stabilization. The library distinguishes itself through its breadth of attribution methods and its support for advanced in
Distributes attribution algorithm calculations across multiple processors or GPUs to speed up processing.
Toolz is a Python library that implements functional programming utilities for iterable transformation, dictionary manipulation, function composition, and lazy evaluation. It provides a set of pure functions designed to work with Python's built-in data structures, enabling concise and composable data processing workflows. What distinguishes toolz is its support for curried partial application, allowing functions to be incrementally applied and reused. It includes dictionary-centric operations that handle nested structures, and offers iterable chain transformers that combine mapping, filtering
Executes functions across multiple cores by serializing input data and aggregating results.
Accelerate is a framework for high-performance array computing that provides a domain-specific language for expressing complex mathematical and parallel computations. By utilizing a declarative programming interface, it allows users to define high-level array transformations that are automatically translated into optimized machine code for diverse hardware architectures. The system distinguishes itself through a modular architecture that decouples high-level array operations from hardware-specific instructions. It employs just-in-time compilation and kernel fusion to transform programs into e
Executes collective operations on multi-dimensional arrays across multicore processors and graphics processing units.
Distributed R is a scalable high-performance platform for the R language. It enables and accelerates large scale machine learning, statistical analysis, and graph processing.
Scalable high-performance platform.
Standard API for Distributed Data Structures in R
Distributed data structures.