TorchLean API

NN.Backend.IR

Backend Planning for IR Graphs #

Adapter from TorchLean's op-tagged IR to backend capsules.

This is intentionally a planning layer, not an evaluator. The graph remains the semantic object; the planner selects which backend contract should implement each node or node family.

Backend operation tag for an IR op.

These tags are the same vocabulary used by backend capsules and runtime reports. If an op maps to a tag that has no capsule for the selected profile, planning fails at the backend boundary instead of silently using a broader bucket.

Instances For

    Backend operation requested by a graph node, if the node needs runtime work.

    Instances For

      Backend choice for one concrete IR node.

      Instances For

        Graph-aware execution plan that preserves the IR node identity for every backend choice.

        Instances For

          Node ids covered by backend kernels, in graph order.

          Instances For

            Selected capsule names, in graph order.

            Instances For

              Plan a single IR node when it corresponds to runtime work.

              Instances For

                Plan every runtime-relevant node in graph order.

                Instances For

                  Check graph well-formedness, then plan every runtime-relevant node.

                  Instances For