# KomputeProject/kompute

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for advanced GPU data processing usecases. Backed by the Linux Foundation.

Repository: https://github.com/KomputeProject/kompute
Canonical: https://ross.abutalabs.com/products/kompute
Homepage: http://kompute.cc/
Language: C++
License: Apache-2.0
License Family: permissive
Topics: vulkan, vulkan-compute, vulkan-example, vulkan-tutorial, vulkan-demos, vulkan-compute-tutorial, vulkan-compute-framework, vulkan-compute-example, cpp, machine-learning, machine-learning-gpu, deep-learning, deep-learning-gpu, gpgpu, gpu-computing, python
Last push: 2026-08-15T13:52:13+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 8, longevity 100
- inputs: {"age_days": 2226, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2558, forks 198 (observed 2026-08-28T04:07:00.795667+00:00)

## What it is
Kompute is a general-purpose GPU compute framework built on Vulkan that works across vendor GPUs (AMD, NVIDIA, Qualcomm, etc.) with both C++ and Python interfaces. It supports asynchronous and parallel GPU operations, mobile deployment via Android NDK, and is a Linux Foundation (LF AI & Data) hosted project.

## Use cases
- run gpu compute shaders across amd nvidia and qualcomm gpus
- accelerate machine learning inference on mobile devices with vulkan
- process tensor data on the gpu from python
- integrate gpu compute into an existing vulkan application
- run parallel asynchronous gpu workloads in c++
- gpu acceleration in game engines like godot
- compute on android devices without cuda

## When to choose
- you need cross-vendor GPU compute without CUDA or vendor lock-in
- you target mobile GPUs via Vulkan and the Android NDK
- you want a lightweight C++/Python layer over Vulkan compute with explicit memory management
- you already have a Vulkan application and want bring-your-own-Vulkan integration

## When to avoid
- you need mature deep-learning training ecosystems like PyTorch or TensorFlow
- you only target NVIDIA GPUs and can use CUDA directly
- you need high-level prebuilt neural network layers rather than raw compute kernels
- your team cannot write or manage SPIR-V compute shaders

## Facets
- artifact type: framework
- maturity: active
- function: gpu-computing, machine-learning, sdk
- domain: gpu-computing, machine-learning, deep-learning, cross-platform, mobile-development
- platform: cpp, python, windows, cross-platform
- tags: vulkan, gpgpu, compute-shaders, spirv, mobile-gpu, tensor-compute, android, linux, macos, mobile

## Member repositories
- KomputeProject/kompute (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:00.795667+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:23:37.444264+00:00, confidence not recorded.
  - readme: https://github.com/KomputeProject/kompute (fetched 2026-08-28T04:07:00.795667+00:00, sha 3180b0696194)
  - homepage: http://kompute.cc/ (fetched 2026-08-29T10:06:15.565751+00:00, sha 098eaa9034d3)
  - site_page: https://kompute.cc/overview/reference.html (fetched 2026-08-29T10:06:15.568631+00:00, sha 99a516aa9bde)
  - site_page: https://kompute.cc/overview/python-reference.html (fetched 2026-08-29T10:06:15.571231+00:00, sha 8bd29e02b7fa)
  - site_page: https://kompute.cc/overview/ci-tests.html (fetched 2026-08-29T10:06:15.573459+00:00, sha fcc4d5a8ce58)
  - site_page: https://kompute.cc/overview/async-parallel.html (fetched 2026-08-29T10:06:15.575459+00:00, sha 31fa95cf8d31)
  - site_page: https://kompute.cc/overview/python-package.html (fetched 2026-08-29T10:06:15.577173+00:00, sha 2a201f004518)
- Data as of 2026-08-30T08:39:29.467469+00:00.