For the complete Mojo documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /docs/manual/basics.md).
Vendor
struct Vendor
Represents GPU vendors.
This struct provides identifiers for different GPU vendors and utility methods for comparison and string representation.
The struct defines a constant for each vendor the stdlib knows about and a
NO_GPU option for systems without an accelerator. It provides comparison
operators and string conversion methods for vendor identification.
It classifies the accelerator the compiler is targeting, which is what
has_amd_gpu_accelerator(), has_nvidia_gpu_accelerator() and
has_apple_gpu_accelerator() report. To identify a specific device, use
GPUInfo.api.
Implemented traits
AnyType,
Copyable,
Deinitable,
Equatable,
ImplicitlyCopyable,
Movable,
RegisterPassable,
TrivialRegisterPassable,
Writable
comptime members
AMD_GPU
comptime AMD_GPU = Vendor(Int8(1))
Represents AMD GPU vendor.
APPLE_GPU
comptime APPLE_GPU = Vendor(Int8(3))
Represents Apple GPU vendor.
NO_GPU
comptime NO_GPU = Vendor(Int8(0))
Represents no GPU or CPU-only execution.
NVIDIA_GPU
comptime NVIDIA_GPU = Vendor(Int8(2))
Represents NVIDIA GPU vendor.
Methods
__eq__
def __eq__(self, other: Self) -> Bool
Checks if two Vendor instances are equal.
Args:
- other (
Self): TheVendorto compare with.
Returns:
Bool: True if vendors are equal, False otherwise.
__ne__
def __ne__(self, other: Self) -> Bool
Checks if two Vendor instances are not equal.
Args:
- other (
Self): TheVendorto compare with.
Returns:
Bool: True if vendors are not equal, False otherwise.
write_to
def write_to(self, mut writer: T)
Writes vendor information to a writer.
Args:
- writer (
T): The writer to output vendor information to.