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
QuantizeDynamicScaledFloat8Pow2Scales
struct QuantizeDynamicScaledFloat8Pow2Scales
Registers the quantization.quantize_dynamic_scaled_float8.pow2_scales graph op.
Same numerics as mo.composite.quantize_dynamic_scaled_fp8 with
float8_e8m0fnu scales, but the power-of-two scales are written widened
to float32, the layout a blockwise fp8 matmul reads. This saves the
separate cast kernel after each quantize.
A custom op rather than an attribute on the composite, as with
row_bounded.
Implemented traitsโ
Methodsโ
executeโ
static def execute[group_size_or_per_token: Int, amax_floor: Float32 = Float32("0")](output: T, scales: T, input: T, scale_ub: Float32, ctx: DeviceContext)