An in-memory IR that supports the full ONNX spec, designed for graph construction, analysis and transformation.
Getting Started
Installation
Via pip:
pip install onnx-ir
Or from source:
pip install git+https://github.com/onnx/ir-py.git
Features ✨
- Full ONNX spec support: all valid models representable by ONNX protobuf, and a subset of invalid models (so you can load and fix them).
- Low memory footprint: mmap'ed external tensors; unified interface for ONNX TensorProto, Numpy arrays and PyTorch Tensors etc. No tensor size limitation. Zero copies.
- Straightforward access patterns: Access value information and traverse the graph topology at ease.
- Robust mutation: Create as many iterators as you like on the graph while mutating it.
- Speed: Performant graph manipulation, serialization/deserialization to Protobuf.
- Pythonic and familiar APIs: Classes define Pythonic apis and still map to ONNX protobuf concepts in an intuitive way.
- No protobuf dependency: The IR does not require protobuf once the model is converted to the IR representation, decoupling from the serialization format.
Concept Diagram
Code Organization 🗺️
_protocols.py: Interfaces defined for all entities in the IR._core.py: Implementation of the core entities in the IR, includingModel,Graph,Node,Value, and others._enums.py: Definition of the type enums that correspond to theDataTypeandAttributeTypeinonnx.proto._name_authority.py: The authority for giving names to entities in the graph, used internally._linked_list.py: The data structure as the node container in the graph that supports robust iteration and mutation. Internal._metadata.py: Metadata store for all entities in the IR.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
onnx_ir-0.1.14.tar.gz
(120.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
onnx_ir-0.1.14-py3-none-any.whl
(139.1 kB
view details)
File details
Details for the file onnx_ir-0.1.14.tar.gz.
File metadata
- Download URL: onnx_ir-0.1.14.tar.gz
- Upload date:
- Size: 120.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bd69e3b5821046d5d7c9d0fdd023f8e1d0cc9a62cbee986fa0e5ab2b1602d7ae
|
|
| MD5 |
515d4b6a76d0a3eef525d5fabccfd2ac
|
|
| BLAKE2b-256 |
a55bebd083a5c3d25ce9f95b34a11b3a492cdcf7831bf127c0f64429a4e83961
|
Provenance
The following attestation bundles were made for onnx_ir-0.1.14.tar.gz:
Publisher:
main.yml on onnx/ir-py
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
onnx_ir-0.1.14.tar.gz -
Subject digest:
bd69e3b5821046d5d7c9d0fdd023f8e1d0cc9a62cbee986fa0e5ab2b1602d7ae - Sigstore transparency entry: 799007208
- Sigstore integration time:
-
Permalink:
onnx/ir-py@28d3943b607ac6fe851e2ef9149ca4c1b07fb852 -
Branch / Tag:
refs/tags/v0.1.14_1 - Owner: https://github.com/onnx
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
main.yml@28d3943b607ac6fe851e2ef9149ca4c1b07fb852 -
Trigger Event:
push
-
Statement type:
File details
Details for the file onnx_ir-0.1.14-py3-none-any.whl.
File metadata
- Download URL: onnx_ir-0.1.14-py3-none-any.whl
- Upload date:
- Size: 139.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
89b212fa7840981c5db5dc478190f1b7369536297c3c6eae68fb1c2237dd2554
|
|
| MD5 |
4f2c5591231d9383ac743bf7368b0fac
|
|
| BLAKE2b-256 |
53d1bd9a5007448b4599a80143b0b5ccc78e9c46176e5e1bee81f6d3da68d217
|
Provenance
The following attestation bundles were made for onnx_ir-0.1.14-py3-none-any.whl:
Publisher:
main.yml on onnx/ir-py
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
onnx_ir-0.1.14-py3-none-any.whl -
Subject digest:
89b212fa7840981c5db5dc478190f1b7369536297c3c6eae68fb1c2237dd2554 - Sigstore transparency entry: 799007210
- Sigstore integration time:
-
Permalink:
onnx/ir-py@28d3943b607ac6fe851e2ef9149ca4c1b07fb852 -
Branch / Tag:
refs/tags/v0.1.14_1 - Owner: https://github.com/onnx
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
main.yml@28d3943b607ac6fe851e2ef9149ca4c1b07fb852 -
Trigger Event:
push
-
Statement type:
