burn-wgpu-0.12.1
- burn-wgpu 0.12.1
- Docs.rs crate page
- MIT OR Apache-2.0
- Links
- Repository
- crates.io
- Source
- Owners
- nathanielsimard
- Dependencies
- burn-common ^0.12.1 normal
  burn-compute ^0.12.1 normal
  burn-fusion ^0.12.1 normal
  burn-tensor ^0.12.1 normal
  bytemuck ^1.14 normal
  derive-new ^0.6.0 normal
  futures-intrusive ^0.5 normal
  hashbrown ^0.14.2 normal
  log ^0.4.20 normal
  num-traits ^0.2.17 normal
  pollster ^0.3 normal
  rand ^0.8.5 normal
  serde ^1.0.192 normal
  spin ^0.9.8 normal
  text_placeholder ^0.5.0 normal
  wgpu ^0.18.0 normal
  burn-autodiff ^0.12.1 dev
  burn-fusion ^0.12.1 dev
  burn-ndarray ^0.12.1 dev
  burn-tensor ^0.12.1 dev
  serial_test ^3.0.0 dev
- Versions
- 100% of the crate is documented
Go to latest version
Platform
Feature flags

docs.rs

Rust

burn_wgpu0.12.1

In burn_wgpu::kernel::reduce

Function burn_wgpu::kernel::reduce::sum

pub fn sum<E: WgpuElement, const D: usize>(
    input: WgpuTensor<E, D>
) -> WgpuTensor<E, 1>

Expand description

Sum all elements in the input buffer.