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
RMSNormQuantizeDynamicScaledFloat8
struct RMSNormQuantizeDynamicScaledFloat8
Registers the quantization.rms_norm_quantize_dynamic_scaled_float8 graph op: mo.composite.reduce.rms_norm fused with a group-scaled (blockwise-FP8) mo.composite.quantize_dynamic_scaled_fp8. Same outputs and scale layout as the unfused pair; group_size_or_per_token must be a proper divisor of the row (per-token scales stay on the rms_norm + quantize composite).
Implemented traitsโ
Methodsโ
executeโ
static def execute[input_type: DType, //, group_size_or_per_token: Int, multiply_before_cast: Bool](output: T, scales: T, input: T, gamma: T, epsilon: Float32, weight_offset: Scalar[input_type], scale_ub: Float32, ctx: DeviceContext)