[object Object][object Object][object Object]undefined[object Object]

Sends token data on the FFN node to the Attention node.

[object Object]

Each operator has calls. First, [object Object] is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, [object Object] is called to perform computation.

[object Object]

• Parameters:

  [object Object]

• Returns

  [object Object]: status code. For details, see .

  The first-phase API implements input parameter validation. The following error codes may be returned.

  [object Object]

[object Object]

• Parameters:

  [object Object]

• Returns

  aclnnStatus status code. For details, see aclnn return codes.

[object Object]

• Deterministic constraints:

  • [object Object] defaults to a deterministic implementation.

• Parameter consistency constraints:

  • The group, worldSize, tokenInfoTableShape, tokenDataShape, and HCCL_BUFFSIZE parameters of all devices must be the same.

• Product constraints:

  • [object Object]Atlas A3 training products/Atlas A3 inference products[object Object]: In this scenario, a single rank contains dual dies. Therefore, the "rank" in the parameter description indicates a single die.

• Shape variable constraints:

  [object Object]undefined

• Constraints on the use of the communication domains:

  • No other operators are allowed in the communication domain of the [object Object] operator.

[object Object]

• Preparing files:

  1. Create the FFNtoAttentionDemo directory, create the aclnnFFNtoAttentionDemo.cpp and FFNtoAttention.sh files in the FFNtoAttentionDemo directory, and modify the files by referring to the following code.

  2. Install the CANN package and compile and run the FFNtoAttentionDemo according to the following instructions.

• FFNtoAttention.sh compilation script

  [object Object]

• Compilation and execution:

  [object Object]

• The sample code is as follows:

  [object Object]