BinaryBuilder

GPUs

Yggdrasil, the community build tree for BinaryBuilder recipes, builds packages for NVIDIA, AMD, Intel and Apple GPUs, and for the cross-vendor OpenCL, Vulkan and SPIR-V standards. Library versions on this page are the latest ones in Julia's General registry when the site was built.

NVIDIA

Yggdrasil recipes that use CUDA are built for 20 of the 21 CUDA toolkits below by default. Each build is tagged with its CUDA version, and Julia installs the one that works with the user's CUDA runtime: a build for CUDA 12.2 works with any CUDA 12 runtime from 12.2 onwards. Program NVIDIA GPUs from Julia with CUDA.jl, and start a recipe from the HelloWorldCUDA example.

CUDA toolkitx86_64ARM servers (SBSA)JetsonBuilt by default
10.2.89✓—✓Opt-in
11.4.4✓✓—Yes
11.5.2✓✓—Yes
11.6.2✓✓—Yes
11.7.1✓✓—Yes
11.8.0✓✓✓Yes
12.0.1✓✓✓Yes
12.1.1✓✓✓Yes
12.2.2✓✓✓Yes
12.3.2✓✓—Yes
12.4.1✓✓✓Yes
12.5.1✓✓✓Yes
12.6.3✓✓✓Yes
12.8.1✓✓✓Yes
12.9.1✓✓✓Yes
13.0.2✓✓✓Yes
13.1.1✓✓✓Yes
13.2.1✓✓✓Yes
13.3.1✓✓✓Yes
13.4.3✓✓✓Yes
13.5.0✓✓✓Yes

From CUDA 13, a single aarch64 build covers both ARM servers and Jetson. Toolkits marked opt-in or preview are left out of CUDA.supported_platforms() by default; recipes include them with its min_version and prereleases keywords.

PackageDescriptionLatest version
CUDNN_jllcuDNN: deep neural network primitives9.28.0
CUTENSOR_jllcuTENSOR: tensor operations2.8.1
CUDSS_jllcuDSS: sparse direct solvers1.0.0
cuSolverMp_jllcuSOLVERMp: distributed dense linear algebra0.8.0
cuQuantum_jllcuQuantum: quantum circuit simulation26.9.0
NCCL_jllNCCL: communication between GPUs2.32.3
TensorRT_jllTensorRT: deep learning inference10.13.0
NVTX_jllNVTX: annotations for profilers3.2.2

AMD

Program AMD GPUs from Julia with AMDGPU.jl.

PackageDescriptionLatest version
AMDGPU_LLVM_Backend_jllLLVM code generator for AMD GPUs23.1.3
ROCmDeviceLibs_jllROCm device libraries7.0.2
hsa_rocr_jllROCm runtime (HSA)5.4.4
HIP_jllHIP runtime5.4.4
rocBLAS_jllrocBLAS: dense linear algebra5.2.3
rocSPARSE_jllrocSPARSE: sparse linear algebra5.2.3
rocRAND_jllrocRAND: random number generation5.2.3
MIOpen_jllMIOpen: deep learning primitives5.2.3
rocminfo_jllrocminfo: device information tool5.4.4

Intel

Program Intel GPUs from Julia with oneAPI.jl.

PackageDescriptionLatest version
NEO_jllCompute runtime for Intel GPUs (NEO)26.35.39758
libigc_jllIntel Graphics Compiler2.41.5
gmmlib_jllIntel graphics memory management library22.10.0
oneAPI_Level_Zero_Loader_jlloneAPI Level Zero loader1.32.0
oneAPI_Level_Zero_Headers_jlloneAPI Level Zero headers1.17.0
oneAPI_Support_jllSupport library for oneAPI.jl0.11.0

Apple

Program Apple GPUs from Julia with Metal.jl.

PackageDescriptionLatest version
Metal_LLVM_Tools_jllLLVM tools for generating Metal code0.5.2
Metal_Shader_Converter_jllMetal shader converter1.1.0

OpenCL, Vulkan and SPIR-V

Use OpenCL from Julia with OpenCL.jl and Vulkan with Vulkan.jl.

PackageDescriptionLatest version
OpenCL_jllOpenCL ICD loader2024.10.24
OpenCL_Headers_jllOpenCL headers2026.5.29
pocl_jllPoCL: portable OpenCL implementation for CPUs7.2.2
intel_opencl_rt_jllIntel OpenCL runtime for x86_64 CPUs2026.1.2
Vulkan_Loader_jllVulkan loader1.3.243
Vulkan_Headers_jllVulkan headers1.4.321
SPIRV_Tools_jllSPIR-V tools2026.4.0
SPIRV_LLVM_Translator_jllTranslator between LLVM IR and SPIR-V23.1.4
SPIRV_LLVM_Backend_jllLLVM code generator for SPIR-V23.1.4

The CUDA toolkits come from Yggdrasil's platforms/cuda.jl each time the site is built.