[object Object]

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

• Description: Performs the backpropagation of [object Object].

• Formula:

  • First, compute [object Object].

    • When the condition rangeOptional[0] ≤ sortedIndices[i] < rangeOptional[1] is met,

      $$tokenGradOut[i] = permutedTokensOutputGrad[sortedIndices[i]-rangeOptional[0]]$$

    • Otherwise,

      $$tokenGradOut[i] = 0$$

  • Then, compute the following:

    $$tokenGradOut = tokenGradOut.reshape(-1, topK, hiddenSize)$$ $$tokenGradOut = tokenGradOut.sum(dim = 1)$$

[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 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 computation:

  • [object Object] defaults to deterministic implementation.

• numTopk <= 512.

• [object Object] cannot be set to [object Object].

• When [object Object] is left empty, [object Object] and [object Object] are ignored, and the execution logic is rolled back to .

[object Object]

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