IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo struct

Struct_grouped_quantize_nvfp4_row_scaled_with_row_indices

struct Struct_grouped_quantize_nvfp4_row_scaled_with_row_indices

Registers the quantization.grouped.quantize.nvfp4.row_scaled.with_row_indices graph op with the graph compiler.

The row-gather variant of quantization.grouped.quantize.nvfp4.row_scaled: output row i quantizes input row row_indices[i] // row_index_divisor, with that row's own scale. A separate op carries the extra operand because graph ops have no optional inputs.

Implemented traitsโ€‹

AnyType, Deinitable, Movable

Methodsโ€‹

executeโ€‹

static def execute[apply_relu2: Int, row_index_divisor: Int](output: T, scales: T, row_scales: T, input: T, row_offsets: T, scales_offsets: T, row_indices: T, context: DeviceContext)

Was this page helpful?