---
name: "rte_ml_op"
section: "3"
platform: "linux"
package: "dpdk-doc"
version: "24.11.4-0+deb13u1"
release: "Debian 13 (Trixie)"
platforms: ["linux"]
url: "https://new.carta.tech/rte_ml_op"
---

# rte\_ml\_op(3)

## NAME

rte\_ml\_op

## SYNOPSIS

`#include <rte_mldev.h>`

### 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**\

## Detailed Description

ML Operation.

This structure contains data related to performing an ML operation on the buffers using the model specified through model\_id.

Definition at line **437** of file **rte\_mldev.h**.

## Field Documentation

### uint16\_t model\_id

Model ID to be used for the operation.

Definition at line **438** 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 **440** of file **rte\_mldev.h**.

### uint32\_t reserved

Reserved for future use.

Definition at line **444** of file **rte\_mldev.h**.

### struct rte\_mempool\* mempool

Pool from which operation is allocated.

Definition at line **446** 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**

struct rte\_ml\_dev\_info::io\_layout

Definition at line **448** 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**

struct rte\_ml\_dev\_info::io\_layout

Definition at line **459** of file **rte\_mldev.h**.

### uint64\_t user\_u64

User data as uint64\_t.

Definition at line **471** of file **rte\_mldev.h**.

### void\* user\_ptr

User data as void\*.

Definition at line **473** of file **rte\_mldev.h**.

### enum rte\_ml\_op\_status status

Operation status.

Definition at line **476** 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 **478** of file **rte\_mldev.h**.

## Author

Generated automatically by Doxygen for DPDK from the source code.