For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Mojo function
quantize_static_scaled_fp8
def quantize_static_scaled_fp8[out_dtype: DType, in_dtype: DType, scale_is_inverted: Bool = True](out_tensor: TileTensor[out_dtype, address_space=out_tensor.address_space, linear_idx_type=out_tensor.linear_idx_type, element_size=out_tensor.element_size], in_tensor: TileTensor[in_dtype, address_space=in_tensor.address_space, linear_idx_type=in_tensor.linear_idx_type, element_size=in_tensor.element_size], scale: Float32, context: DeviceContext)
TileTensor implementation of static scaled FP8 quantization.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!