cubecl-cuda 0.6.0

CUDA runtime for CubeCL
Documentation

cubecl-cuda

There is very little structured metadata to build this page from currently. You should check the main library docs, readme, or Cargo.toml in case the author documented the features in them.

This version has 24 feature flags, 1 of them enabled by default.

default

std (default)

compilation-cache

conv_tests

matmul_tests_all

matmul_tests_alt_shapes

matmul_tests_barrier

matmul_tests_base

matmul_tests_cyclic

matmul_tests_double

matmul_tests_f16

matmul_tests_f32

matmul_tests_hybrid

matmul_tests_hypercube

matmul_tests_layouts

matmul_tests_ordered

matmul_tests_partition_buffering

matmul_tests_plane

matmul_tests_simple

matmul_tests_specialized

matmul_tests_strided

matmul_tests_tilewise

matmul_tests_tma

matmul_tests_unit

ptx-wmma

This feature flag does not enable additional features.