Skip to main content

Mojo function

quantize_dynamic_block_scaled

quantize_dynamic_block_scaled[out_dtype: DType, scales_dtype: DType, in_dtype: DType, //, *, SF_VECTOR_SIZE: Int, target: StringSlice[StaticConstantOrigin] = StringSlice("cpu")](output_device: TileTensor[out_dtype, linear_idx_type=output_device.linear_idx_type, element_size=output_device.element_size], scales_device: TileTensor[scales_dtype, linear_idx_type=scales_device.linear_idx_type, element_size=scales_device.element_size], input_device: TileTensor[in_dtype, linear_idx_type=input_device.linear_idx_type, element_size=input_device.element_size], tensor_sf: Float32, ctx: DeviceContext)