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

RMSNormQuantizeDynamicScaledFloat8Dual

struct RMSNormQuantizeDynamicScaledFloat8Dual

Registers the mo.rms_norm_quantize_dynamic_scaled_float8.dual graph op: mo.reduce.rms_norm fused with a group-scaled (blockwise-FP8) mo.quantize_dynamic_scaled_float8, keeping the normalized row as a third output for the norm's other readers. Same outputs and scale layout as the unfused pair; group_size_or_per_token must be a proper divisor of the row.

Implemented traitsโ€‹

AnyType, Deinitable, Movable

Methodsโ€‹

executeโ€‹

static def execute[group_size_or_per_token: Int, multiply_before_cast: Bool, weight_offset: Float32](normed: T, output: T, scales: T, input: T, gamma: T, epsilon: Float32, scale_ub: Float32, ctx: DeviceContext)

Was this page helpful?