kempnerpulse.compute.presets

Real Utilization weight presets.

A preset is a 4-tuple of weights (sm, tensor, dram, gr) applied to the four Real Utilization composite inputs. The weights of a preset sum to 1.0; a custom weight tuple is auto-normalized by the caller before use. Presets let the same composite emphasize different subsystems for AI, HPC, or memory-bound workloads.

Functions

preset_name_for_weights(weights)	Name a weight tuple: "ai" / "hpc" / "mem", else "custom".
resolve_preset(name)	Return the weight tuple for a preset name.

kempnerpulse.compute.presets.resolve_preset(name)

Return the weight tuple for a preset name.

Raises KeyError (with the known names) if the name is not a built-in preset.

Parameters:

name (str)

Return type:

Tuple[float, float, float, float]

kempnerpulse.compute.presets.preset_name_for_weights(weights)

Name a weight tuple: "ai" / "hpc" / "mem", else "custom".

A tuple matches a built-in preset only when every weight is within a small floating-point tolerance of that preset’s weights.

Parameters:

weights (Tuple[float, float, float, float])

Return type:

str