Data Fields¶

uint16_t model_id
uint16_t nb_batches
uint32_t reserved
struct rte_mempool * mempool
struct rte_ml_buff_seg ** input
struct rte_ml_buff_seg ** output
enum rte_ml_op_status status
uint64_t impl_opaque
uint64_t user_u64
void * user_ptr

uint16_t model_id¶

Model ID to be used for the operation.

Definition at line 424 of file rte_mldev.h.

uint16_t nb_batches¶

Number of batches. Minimum value must be one. Input buffer must hold inference data for each batch as contiguous.

Definition at line 426 of file rte_mldev.h.

uint32_t reserved¶

Reserved for future use.

Definition at line 430 of file rte_mldev.h.

struct rte_mempool* mempool¶

Pool from which operation is allocated.

Definition at line 432 of file rte_mldev.h.

struct rte_ml_buff_seg** input¶

Array of buffer segments to hold the inference input data.

When the model supports IO layout RTE_ML_IO_LAYOUT_PACKED, size of the array is 1.

When the model supports IO layout RTE_ML_IO_LAYOUT_SPLIT, size of the array is rte_ml_model_info::nb_inputs.

See also:

Definition at line 434 of file rte_mldev.h.

struct rte_ml_buff_seg** output¶

Array of buffer segments to hold the inference output data.

When the model supports IO layout RTE_ML_IO_LAYOUT_PACKED, size of the array is 1.

When the model supports IO layout RTE_ML_IO_LAYOUT_SPLIT, size of the array is rte_ml_model_info::nb_outputs.

See also:

Definition at line 445 of file rte_mldev.h.

uint64_t user_u64¶

User data as uint64_t.

Definition at line 457 of file rte_mldev.h.

void* user_ptr¶

User data as void*.

Definition at line 459 of file rte_mldev.h.

enum rte_ml_op_status status¶

Operation status.

Definition at line 462 of file rte_mldev.h.

uint64_t impl_opaque¶

Implementation specific opaque value. An implementation may use this field to hold implementation specific value to share between dequeue and enqueue operation. The application should not modify this field.

Definition at line 464 of file rte_mldev.h.