ServingScenario
Serving scenarios · Implementation: mlsysim/engine/scenario_definitions/serving.py.
Construct this scenario with keyword inputs. The fields below show the types and defaults declared by this class.
Serving workload on hardware at a stated context and batch (ServingModel).
Notes
Equation: Compose mlsysim.solvers.ServingModel.
Assumptions: The stated fields are inputs to mlsysim.solvers.ServingModel; its documented validity regime, units, and modeling choices apply unchanged.
Excludes: This scenario adds no measurement, empirical calibration, or mechanisms beyond mlsysim.solvers.ServingModel.
References
Derivation: this scenario binds its input fields to the referenced implementation contracts: mlsysim.solvers.ServingModel. The methods below identify any additional arithmetic.
Examples
>>> from mlsysim import Scenarios
>>> case = Scenarios.Llama3_70B_ServingH100
>>> type(case.result).__name__
'ServingResult'Attributes
| Name | Description |
|---|---|
| batch_size | |
| hardware | |
| result | Evaluate this scenario through mlsysim.solvers.ServingModel.solve. Equation: pass |
| seq_len | |
| workload |
workload
Type: Workload.
Declared default: required.
hardware
Type: HardwareNode.
Declared default: required.
seq_len
Type: int.
Declared default: required.
batch_size
Type: int.
Declared default: 1.
result
engine.scenario_types.ServingScenario.result
Evaluate this scenario through mlsysim.solvers.ServingModel.solve. Equation: pass the stated fields to that implementation; its contract defines the calculation and feasibility tests. Units: each returned field follows the referenced result schema; no independent equation is evaluated by this wrapper.