[object Object]

[object Object][object Object]undefined
[object Object]
  • Processes and combines the MoE FFN output during MoE computation.
  • Formula:expertid=expandedExpertIdx[i,k]expertid=expandedExpertIdx[i,k] out(i,j)=x1i,j+x2Optionali,j+k=0K(scalesi,k(expandedXexpandedRowIdxi+knumrows,j+biasexpertid,j))out(i,j)=x1_{i,j}+x2Optional_{i,j}+\sum_{k=0}^{K}(scales_{i,k}*(expandedX_{expandedRowIdx_{i+k*num_rows},j}+bias_{expertid,j}))
[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]
[object Object]
[object Object]
  • Parameters:

    [object Object]
  • Returns:

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

    The first-phase API implements input parameter verification. The following errors may be thrown:

    [object Object]
[object Object]
  • Parameters:

    [object Object]
  • Returns:

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

[object Object]
  • Deterministic computing:
    • [object Object] defaults to a deterministic implementation.
[object Object]

The following example is for reference only. For details, see .

[object Object]