org.bytedeco.pytorch.cuda

Class AOTIModelContainerRunnerCuda

java.lang.Object

org.bytedeco.javacpp.Pointer

org.bytedeco.pytorch.AOTIModelContainerRunner

org.bytedeco.pytorch.cuda.AOTIModelContainerRunnerCuda

All Implemented Interfaces:

AutoCloseable

@Namespace(value="torch::inductor")
 @Properties(inherit=torch_cuda.class)
public class AOTIModelContainerRunnerCuda
extends AOTIModelContainerRunner

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

address, capacity, limit, position

Constructor Summary

Constructors

Constructor and Description
AOTIModelContainerRunnerCuda(BytePointer model_so_path)
AOTIModelContainerRunnerCuda(BytePointer model_so_path, long num_models, BytePointer device_str, BytePointer cubin_dir)
AOTIModelContainerRunnerCuda(Pointer p) Pointer cast constructor.
AOTIModelContainerRunnerCuda(String model_so_path)
AOTIModelContainerRunnerCuda(String model_so_path, long num_models, String device_str, String cubin_dir)

Method Summary

Modifier and Type	Method and Description
TensorVector	run_with_cuda_stream(TensorVector inputs, CUDAStream cuda_stream)
TensorVector	run(TensorVector inputs)

Methods inherited from class org.bytedeco.pytorch.AOTIModelContainerRunner

get_call_spec, getConstantNamesToDtypes, getConstantNamesToOriginalFQNs, run_const_fold, swap_constant_buffer, update_constant_buffer, update_inactive_constant_buffer

Methods inherited from class org.bytedeco.javacpp.Pointer

address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, withDeallocator, zero

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

AOTIModelContainerRunnerCuda

public AOTIModelContainerRunnerCuda(Pointer p)

Pointer cast constructor. Invokes Pointer(Pointer).

AOTIModelContainerRunnerCuda

public AOTIModelContainerRunnerCuda(@StdString
                                    BytePointer model_so_path,
                                    @Cast(value="size_t")
                                    long num_models,
                                    @StdString
                                    BytePointer device_str,
                                    @StdString
                                    BytePointer cubin_dir)

AOTIModelContainerRunnerCuda

public AOTIModelContainerRunnerCuda(@StdString
                                    BytePointer model_so_path)

AOTIModelContainerRunnerCuda

public AOTIModelContainerRunnerCuda(@StdString
                                    String model_so_path,
                                    @Cast(value="size_t")
                                    long num_models,
                                    @StdString
                                    String device_str,
                                    @StdString
                                    String cubin_dir)

AOTIModelContainerRunnerCuda

public AOTIModelContainerRunnerCuda(@StdString
                                    String model_so_path)

Method Detail

run

@ByVal
public TensorVector run(@ByRef
                               TensorVector inputs)

Overrides:

run in class AOTIModelContainerRunner

run_with_cuda_stream

@ByVal
public TensorVector run_with_cuda_stream(@ByRef
                                                TensorVector inputs,
                                                @ByVal
                                                CUDAStream cuda_stream)