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