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_dequant_nvfp4

struct Struct_dequant_nvfp4

Registers the quantization.dequant.nvfp4 graph op with the graph compiler.

Dequantizes packed NVFP4 weights to bfloat16 or float32. scales is either the rank-2 [N, K // 16] checkpoint layout or the rank-5 SM100 interleaved layout, and tensor_sf is the tensor-wide decode scale (weight_scale_2).

Implemented traitsโ€‹

AnyType, Deinitable, Movable

Methodsโ€‹

executeโ€‹

static def execute(output: T, input: T, scales: T, tensor_sf: Float32, context: DeviceContext)

Was this page helpful?