TensorRT Plan
AI & Machine LearningPLAN may store a serialized TensorRT engine or producer-specific data from another application. A TensorRT plan is an inference artifact built for runtime conditions, not an editable training model. Establish loading requirements and source model.
- What it is used for
- Persisting TensorRT inference plans or producer-specific data
- What the file contains
- Producer-dependent
All sections, questions and sources
Content reviewed： · Editor：Kai
Opening steps
Choose your environment or purpose to see its steps.
Menu labels and support vary by app, OS and version. Preserve the original before making changes.
Troubleshooting by symptom
- Different version fails: check configured version compatibility and runtime requirements.
- Missing plugin: establish required implementations and legitimate sources.
- Text editor cannot read it: a TensorRT plan is not an ordinary planning document.
- Renamed plan rejected as ONNX: locate the source graph; optimized artifacts are distinct.
- Shape fails: inspect build-time minimum/optimal/maximum shapes and selected profile.
- Missing plugin: compare required build/runtime plugin libraries.
PLAN → rebuild from the original model for the intended runtime
- Obtain original model, I/O, compatibility mode and build procedure.
- Build for the target GPU/runtime and compare against original predictions.
- Compare output shapes, values and timing with the same input before/after export; retain definitions and export settings.
The plan alone may not recover original training structure/weights; renaming is not runtime migration.
Plans versus rebuild inputs
A plan is an optimized runtime artifact, not a universal editable source; retain ONNX/source data and build settings.
Deserialization loads executable artifacts; avoid deserializing unknown files merely to inspect them.
Source for these steps：NVIDIA · Engine Compatibility / NVIDIA · Build your first engine / NVIDIA · TensorRT C++ API documentation
Record input profiles and precision
Dynamic input profiles constrain execution; arbitrary shapes may not be accepted.
Compare accuracy and performance on the same data after precision changes; retain source, build logs and reference outputs.
Source for these steps：NVIDIA · Engine Compatibility / NVIDIA · Build your first engine / NVIDIA · TensorRT C++ API documentation
Related-format differences
| Format | Main role | What to check |
|---|---|---|
| ENGINE / PLAN | TensorRT runtime artifact | Check build requirements |
| ONNX | Inference graph interchange | May serve as rebuild input |
| PT / KERAS | Source-framework serialization | Retain definitions/preprocessing |
Handling and security
TensorRT engines may contain executable code and plugin dependencies. Do not deserialize/run untrusted engines or enable host-code permissions merely to make an unknown plan load.
Questions and answers
Is PLAN a schedule document?
It may be a TensorRT artifact; identify origin.
Will renaming to ENGINE fix compatibility?
It does not change internal build conditions.
Are nearby versions necessarily compatible?
Check supported versions and configured compatibility modes.
Do ENGINE and PLAN suffixes require conversion?
Both are used as serialized-artifact names; inspect contents and producer workflow.
Do compatibility flags make it universal?
Modes have limits; check platform, version, hardware and plugin requirements.
Format facts: name, steward and MIME type
- Formal name
- TensorRT engine plan (common use)
- Steward / specification
- NVIDIA TensorRT / producer-specific uses
- MIME type
- Depends on the producer or server; an extension alone does not establish a MIME type.
Primary and official sources
- Official documentationEngine Compatibility
Documents TensorRT/GPU compatibility and trusted engine handling.
NVIDIA · Link checked： - Official documentationBuild your first engine
Build and validate an engine from ONNX.
NVIDIA · Link checked： - Official documentationTensorRT C++ API documentation
Documents deserializing only trusted engines.
NVIDIA · Link checked：