greedy_planner

GreedyMemoryPlanner API

The GreedyMemoryPlanner class implements a greedy algorithm for memory allocation in the context of AOT (Ahead-Of-Time) compilation for machine learning models. It is designed to optimize memory usage by reusing gaps from tensors whose lifetimes have ended.

Classes:

• GreedyMemoryPlanner –

  Implements a greedy memory allocation strategy for tensors in a shared buffer.

Copyright 2025 Ambiq. All Rights Reserved.

Classes

GreedyMemoryPlanner

GreedyMemoryPlanner(target: SocPlatform)

Greedy memory planner for AOT models.

Functions

plan

plan(model: AirModel, memory_constraints: list[MemoryConstraint] | None = None, tensor_constraints: list[AttributeRuleset] | None = None) -> MemoryPlan

Allocate offsets for each tensor in a shared buffer using a first-fit algorithm that reuses gaps from tensors whose lifetimes have ended. This version also merges contiguous free blocks, and if the last free block aligns with the current offset, that block will be used for allocation.

Parameters:

• model

  (AirModel) –

  The target model.

• memory_constraints

  (list[MemoryConstraint] | None, default: None ) –

  Memory constraints

• tensor_constraints

  (list[AttributeRuleset] | None, default: None ) –

  Tensor constraints

Returns:

• MemoryPlan ( MemoryPlan ) –

  The memory plan containing tensor allocations and arena usages.

Functions