ONNX Runtime
|
CUDA Provider Options. More...
#include <onnxruntime_c_api.h>
Public Member Functions | |
OrtCUDAProviderOptions () | |
Public Attributes | |
int | device_id |
CUDA device Id Defaults to 0. | |
OrtCudnnConvAlgoSearch | cudnn_conv_algo_search |
CUDA Convolution algorithm search configuration. See enum OrtCudnnConvAlgoSearch for more details. Defaults to OrtCudnnConvAlgoSearchExhaustive. | |
size_t | gpu_mem_limit |
CUDA memory limit (To use all possible memory pass in maximum size_t) Defaults to SIZE_MAX. | |
int | arena_extend_strategy |
Strategy used to grow the memory arena 0 = kNextPowerOfTwo 1 = kSameAsRequested Defaults to 0. | |
int | do_copy_in_default_stream |
Flag indicating if copying needs to take place on the same stream as the compute stream in the CUDA EP 0 = Use separate streams for copying and compute. 1 = Use the same stream for copying and compute. Defaults to 1. WARNING: Setting this to 0 may result in data races for some models. Please see issue #4829 for more details. | |
int | has_user_compute_stream |
Flag indicating if there is a user provided compute stream Defaults to 0. | |
void * | user_compute_stream |
User provided compute stream. If provided, please set has_user_compute_stream to 1. | |
OrtArenaCfg * | default_memory_arena_cfg |
CUDA memory arena configuration parameters. | |
int | tunable_op_enable |
Enable TunableOp for using. Set it to 1/0 to enable/disable TunableOp. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_CUDA_TUNABLE_OP_ENABLE. | |
int | tunable_op_tuning_enable |
Enable TunableOp for tuning. Set it to 1/0 to enable/disable TunableOp tuning. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_CUDA_TUNABLE_OP_TUNING_ENABLE. | |
int | tunable_op_max_tuning_duration_ms |
Max tuning duration time limit for each instance of TunableOp. Defaults to 0 to disable the limit. | |
CUDA Provider Options.
|
inline |
int OrtCUDAProviderOptions::arena_extend_strategy |
Strategy used to grow the memory arena 0 = kNextPowerOfTwo
1 = kSameAsRequested
Defaults to 0.
OrtCudnnConvAlgoSearch OrtCUDAProviderOptions::cudnn_conv_algo_search |
CUDA Convolution algorithm search configuration. See enum OrtCudnnConvAlgoSearch for more details. Defaults to OrtCudnnConvAlgoSearchExhaustive.
OrtArenaCfg* OrtCUDAProviderOptions::default_memory_arena_cfg |
CUDA memory arena configuration parameters.
int OrtCUDAProviderOptions::device_id |
CUDA device Id Defaults to 0.
int OrtCUDAProviderOptions::do_copy_in_default_stream |
Flag indicating if copying needs to take place on the same stream as the compute stream in the CUDA EP 0 = Use separate streams for copying and compute. 1 = Use the same stream for copying and compute. Defaults to 1. WARNING: Setting this to 0 may result in data races for some models. Please see issue #4829 for more details.
size_t OrtCUDAProviderOptions::gpu_mem_limit |
CUDA memory limit (To use all possible memory pass in maximum size_t) Defaults to SIZE_MAX.
int OrtCUDAProviderOptions::has_user_compute_stream |
Flag indicating if there is a user provided compute stream Defaults to 0.
int OrtCUDAProviderOptions::tunable_op_enable |
Enable TunableOp for using. Set it to 1/0 to enable/disable TunableOp. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_CUDA_TUNABLE_OP_ENABLE.
int OrtCUDAProviderOptions::tunable_op_max_tuning_duration_ms |
Max tuning duration time limit for each instance of TunableOp. Defaults to 0 to disable the limit.
int OrtCUDAProviderOptions::tunable_op_tuning_enable |
Enable TunableOp for tuning. Set it to 1/0 to enable/disable TunableOp tuning. Otherwise, it is disabled by default. This option can be overriden by environment variable ORT_CUDA_TUNABLE_OP_TUNING_ENABLE.
void* OrtCUDAProviderOptions::user_compute_stream |
User provided compute stream. If provided, please set has_user_compute_stream
to 1.