Docs.rs
cubecl-convolution-0.7.0
cubecl-convolution 0.7.0
Docs.rs crate page
MIT
OR
Apache-2.0
Links
Repository
crates.io
Source
Owners
nathanielsimard
Dependencies
bytemuck ^1.16.1
normal
cubecl-common ^0.7.0
normal
cubecl-core ^0.7.0
normal
cubecl-matmul ^0.7.0
normal
cubecl-random ^0.7.0
normal
cubecl-reduce ^0.7.0
normal
cubecl-runtime ^0.7.0
normal
cubecl-std ^0.7.0
normal
half ^2.5
normal
pretty_assertions ^1.4
normal
optional
serde ^1.0.204
normal
trybuild ^1
dev
Versions
20.43%
of the crate is documented
Go to latest version
Platform
aarch64-apple-darwin
aarch64-unknown-linux-gnu
i686-pc-windows-msvc
x86_64-pc-windows-msvc
x86_64-unknown-linux-gnu
Feature flags
docs.rs
About docs.rs
Badges
Builds
Metadata
Shorthand URLs
Download
Rustdoc JSON
Build queue
Privacy policy
Rust
Rust website
The Book
Standard Library API Reference
Rust by Example
The Cargo Guide
Clippy Documentation
Module kernels
cubecl_
convolution
0.7.0
Module kernels
Module Items
Modules
In crate cubecl_
convolution
cubecl_convolution
Module
kernels
Copy item path
Source
Modules
ยง
layered
The layered matmul combines multiple component-based algorithm implementations with selection logic to pick the optimal kernel for a set of parameters.