Releases: onnx/ir-py
Releases · onnx/ir-py
v0.1.4
What's Changed
Note
This release includes a fix to the 4 bit dtype handling logic in the TensorProtoTensor.numpy()
method. You should update to this version if you use onnx-ir to process 4 bit tensor data (uint4, int4, float4e2m1) numerically with NumPy.
Bug Fixes
- Fix 4bit tensor unpacking by @justinchuby in #118
API
- [DataType] Add is_integer and is_signed queries by @iksnagreb in #110
Documentation
- Add versionadded in docs for enum methods by @justinchuby in #113
Other Changes
- Bump version to 0.1.4 by @justinchuby in #111
- Update CONTRIBUTING on DCO by @justinchuby in #112
- Create py.typed to allow type checkers by @justinchuby in #114
- Move py.typed by @justinchuby in #115
New Contributors
- @iksnagreb made their first contribution in #110
Full Changelog: v0.1.3...v0.1.4
v0.1.3
What's Changed
API
- Create adapters for torch by @justinchuby in #94
- Expose DeduplicateInitializersPass in common passes module by @copilot-swe-agent in #99
Graph Passes
- Add deduplication pass for initializer tensors by @AbhishekHerbertSamuel in #67
- [Pass] Support CSE constant nodes by @titaiwangms in #92
Bug fixes
- Support numpy scalars in
Tensor
by @justinchuby in #102
Documentation
- Document changes between versions in docstrings by @justinchuby in #105
- Create CONTRIBUTING.md with development setup and lintrunner guidance by @copilot-swe-agent in #107
Other Changes
- Bump version to 0.1.3 by @justinchuby in #91
- [docs] Expose ir_tensor_adapters by @justinchuby in #95
- Set up copilot by @justinchuby in #97
New Contributors
- @AbhishekHerbertSamuel made their first contribution in #67
- @copilot-swe-agent made their first contribution in #99
Full Changelog: v0.1.2...v0.1.3
v0.1.2
What's Changed
API
- Support initializers with onnxtext by @justinchuby in #60
- Implement all_nodes() and subgraphs() as convenience methods by @justinchuby in #76
- Update from_onnx_text method by @justinchuby in #80
- External data callback and ir.save fixes by @justinchuby in #85
- Convenience function get_const_tensor by @justinchuby in #45
Graph Passes
- [pass] Check post conditions on the resulting model by @justinchuby in #78
Documentation
- Improve docs for attributes and initializers by @justinchuby in #64
- Create logos for the documentation site by @justinchuby in #65
- Set autodoc_typehints to descriptions in docs by @justinchuby in #68
- Improve docstrings by @justinchuby in #75
- Use copilot to improve documentation by @justinchuby in #88
- Add PackedTensor and MetadataStore to docs by @justinchuby in #90
Other Changes
- Bump version to 0.1.2 by @justinchuby in #61
- [Easy] Update name as ir-py instead of onnx-ir by @jcwchen in #49
- Improve README.md by @xadupre in #71
- Print value type in Tensor init error message by @justinchuby in #74
- Create PackedTensor for representing 4bit tensors by @justinchuby in #89
- Ban onnx imports by @justinchuby in #87
New Contributors
Full Changelog: v0.1.1...v0.1.2
v0.1.1
What's Changed
API
- Create
add
methods on initializers and attributes by @justinchuby in #33
Core
- Prevent values produced by other nodes to be added as graph inputs by @justinchuby in #51
Graph Passes
- [pass] Add CSE by @titaiwangms in #36
Bug fixes
- Revert changes to LiftConstantsToInitializersPass by @justinchuby in #41
Documentation
- Remove RefAttr from docs because it is not a class by @justinchuby in #35
- Create release.yml for generating release notes by @justinchuby in #52
Other Changes
- Rename reuse job to make required by @justinchuby in #37
- Configure the do-not-merge bot by @justinchuby in #40
- Bump version number to v0.1.1 by @justinchuby in #42
- Update codecov.yml to ignore unit tests by @justinchuby in #53
New Contributors
- @titaiwangms made their first contribution in #36
Full Changelog: v0.1.0...v0.1.1
v0.1.0
First official release of the onnx_ir package.