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
QuantizeTensorDynamicScaledFloat8
struct QuantizeTensorDynamicScaledFloat8
Registers the quantization.quantize_tensor_dynamic_scaled_float8 graph op with the graph compiler.
Implemented traitsโ
Methodsโ
executeโ
static def execute[group_size_or_per_token: Int](output: T, scales: T, input: T, scale_ub: Float32, ctx: DeviceContext)