A fused operator of [object Object] and [object Object]. It performs a "combine" operation on the output of the [object Object] computation based on specified indices. [object Object] supports the AI processor-affinity format (NZ).
Compared with , this API supports the INT4 weight matrix and introduces the input parameters [object Object], [object Object], [object Object], and [object Object]. The first three parameters are reserved and do not take effect currently. Pass a null pointer for them. [object Object] is used for performance tuning. The first value in the array indicates the expected number of tokens to be processed by each expert. Operator tiling is performed based on this expected value to achieve higher performance. Select the appropriate API as required.
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.
Parameters
[object Object]Return
[object Object]status code. For details, see .The first-phase API implements input parameter validation. The following errors may be thrown:
[object Object]
Deterministic computation:
[object Object]defaults to non-deterministic implementation. You can call[object Object]to enable deterministic computation.
The input and output support the following data type combinations.
[object Object]undefined
The following example is for reference only. For details, see .