[object Object]

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

• This API is used to quantize each group at the granularity of basic blocks to FP8/HiFP8 based on the input start value of the group index (groupList), and output the quantization parameter scale (FP32).

• Formula:

  $$input\_max = block\_reduce\_max(abs(input))$$ $$scale = min(input\_max/FP8\_MAX(HiF8\_MAX), 1/min\_scale)$$ $$y = cast\_to\_[HiF8/FP8](input/scale)$$

[object Object]

Each operator has calls. You must call aclnnGroupedDynamicBlockQuantGetWorkspaceSize to obtain the workspace size required for computation and the executor that contains the operator computation process, and then call aclnnGroupedDynamicBlockQuant to perform the 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

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

[object Object]

• Deterministic description: aclnnGroupedDynamicBlockQuant is implemented in deterministic mode by default.

[object Object]

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