Skip to main content

Crate oneliner_runtime

Crate oneliner_runtime 

Source

Structs§

A2
2-byte alignment
A4
4-byte alignment
A16
16-byte alignment
A32
32-byte alignment
A64
64-byte alignment
Aligned
A newtype with alignment of at least A bytes
ArenaStorage
Only stores the large arena value.
Buffer
BufferMut
BufferRange
ModelArtifacts
OwnedArena
Instance-owned model arena storage selected by the Oneliner alloc feature.
SequentialExecutor
Executor that runs work items immediately in submission order.
SharedArena
Tensor4D
Four-dimensional tensor backed by an owned, aligned, fixed-size nested array.
WorkItem
iree_hal_executable_dispatch_state_v0_t
iree_hal_executable_environment_v0_t
iree_hal_executable_library_header_t
iree_hal_executable_workgroup_state_v0_t
iree_hal_processor_v0_t

Enums§

Access
AnyBuffer
Error

Traits§

BufferSource
Converts a generated storage item into the BufferRef used by dispatch.
Executor
Schedules work items and provides a completion barrier.
ModelInference
Typed tensor inference implemented directly by generated model instances.
ModelSource
Metadata exposed by a model generated with #[model].

Functions§

Aligned
Changes the alignment of value to be at least A bytes
concurrent
Runs a group of generated commands sequentially.
dispatch⚠
Dispatches an IREE workload and panics on failure.
dispatch_fn_from_library⚠
Resolves an export ordinal from an IREE static library.
fill⚠
Fills a generated buffer range with one byte value.
try_dispatch⚠
Dispatches an IREE workload with the default executor.
try_dispatch_with_executor⚠
Dispatches an IREE workload through a caller-provided executor.

Type Aliases§

AlignedType
AnyBufferRange
DefaultExecutor
DispatchFn
Shape
Tensor
TensorArray
iree_hal_executable_import_thunk_v0_t
iree_hal_executable_import_v0_t
iree_hal_executable_library_query_fn_t