Use onnx_ir as a dependency (#2324)

Take `onnx_ir` as a dependency and expose onnxscript.ir as an alias of
`onnx_ir`.

Author: justinchuby

.github/workflows/main.yaml

@@ -31,6 +31,7 @@ jobs:
           - py311-torch-nightly
           - py311-onnx-weekly
           - py311-ort-nightly
+          - py311-onnx-ir-git
           - py310
         include:
           - name: py312
@@ -51,6 +52,9 @@ jobs:
           - name: py311-ort-nightly
             python-version: "3.11"
             nox-tag: test-ort-nightly
+          - name: py311-onnx-ir-git
+            python-version: "3.11"
+            nox-tag: test-onnx-ir-git
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4

README.md

@@ -17,8 +17,6 @@ models using a subset of Python. ONNX Script is:
 
 This repo also covers:
 
-* **ONNX IR:** an in-memory IR that supports the full ONNX spec, designed
-  for graph construction, analysis and transformation.
 * **ONNX Script Optimizer:** provides functionality to optimize an ONNX
   model by performing optimizations and clean-ups such as constant folding,
   dead code elimination, etc.
@@ -152,24 +150,6 @@ result = Hardmax(v)
 
 More examples can be found in the [docs/examples](docs/examples) directory.
 
-## ONNX IR
-
-An in-memory IR that supports the full ONNX spec, designed for graph construction, analysis and transformation.
-
-### 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.
-
 ## ONNX Script Tools
 
 ### ONNX Optimizer

docs/ir/getting_started.ipynb

@@ -1,23 +1,5 @@
 # ONNX IR
 
-An in-memory IR that supports the full ONNX spec, designed for graph construction, analysis and transformation.
+ONNX IR is now an official ONNX project! Documentation has been migrated to [onnx.ai/ir-py/](https://onnx.ai/ir-py/).
 
-## 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.
-
-## Get started
-
-```{toctree}
-:maxdepth: 1
-
-getting_started
-tensors
-ir_api/index
-```
+You may continue to use `onnxscript.ir` unchanged for compatibility with older (<0.3) versions of ONNX Script.