Port onnx float16 from onnxconverter-common #86

bjeffrey92 · 2025-06-17T12:21:01Z

A few weeks ago I created an issue on the onnx library repo enquiring about the state of the onnxconverter-common library, which appears to no longer be actively maintained. @justinchuby responded to me and suggested that the module of onnxconverter-common which I require, for converting a single precision onnx model to mixed precision, could be ported into this library.

Here, I have ported the relevant functions from the float16 module from onnxconverter-common (https://github.com/microsoft/onnxconverter-common/blob/master/onnxconverter_common/float16.py) to this repo at the location suggested by @justinchuby. I also copied the relevant tests across.

Note, that this is not originally my code, hence I have retained the attribution and the original MIT license information with the source code. The modifications I made were just to:

strip out some functions that are not needed for my use case
add type hinting throughout
apply formatting and linting rules specified in the ir-py repo
I have not made any material change to the logic of any of the functions in the original module in onnxconverter-common.

justinchuby · 2025-06-17T14:16:26Z

Thank you - for this pass we would want to replace onnx.helper usages with relavant onnx_ir apis. Could you do that?

justinchuby · 2025-06-17T14:17:38Z

You can start by removing the imports onnx, helper and onnx_proto.

justinchuby · 2025-06-17T14:18:23Z

You may also refer to the rest of the files in the passes directory for examples

bjeffrey92 · 2025-06-18T08:51:38Z

@justinchuby thanks for looking at this so quickly, but can you be a bit more specific please? I don't see any functions in the other modules of the passes directory which look like they replicate the onnx.helper and onnx.numpy_helper functions that are used here (onnx.helper.make_node, onnx.helper.make_tensor_value_info, onnx.numpy_helper.to_array)

bjeffrey92 · 2025-06-18T08:53:40Z

@justinchuby and when you say that you want me to remove the onnx_proto import, do you mean just import the protos from the top level of the onnx library, eg onnx.ModelProto rather onnx.onnx_pb.ModelProto?

Like how it is referenced here: https://github.com/onnx/ir-py/blob/main/src/onnx_ir/passes/common/shape_inference.py#L22

justinchuby · 2025-06-18T14:26:52Z

Sorry I forgot to mention: the shape inference and checker passes are the only two not to reference because they need to directly use onnx apis. You many see https://github.com/onnx/ir-py/blob/main/src/onnx_ir/passes/common/constant_manipulation.py as an example.

The essential idea is this: onnx_ir provides a complete set of apis to manipulate an onnx graph so you don’t need to work directly with protobuf. Therefore any import from the onnx package in a graph transformation pass is not needed. I.e. onnx.numpy_helper, onnx.helper etc. that will directly generate protobuf objects should not be used.

justinchuby · 2025-06-18T14:27:59Z

You may find the api documentation here: https://onnx.ai/ir-py/api/index.html as well as an ai generated version: https://deepwiki.com/onnx/ir-py

justinchuby · 2025-06-18T15:11:22Z

Specifically you may use:

onnx.helper.make_node: ir.node()
onnx.helper.make_tensor_value_info: value.shape=..., value.dtype=...
onnx.numpy_helper.to_array: ir.tensor()

…ter-common Signed-off-by: bjeffrey92 <[email protected]>

Signed-off-by: bjeffrey92 <[email protected]>

src/onnx_ir/passes/common/onnx_float_16.py

+
+import numpy as np
+import numpy.typing as npt
+import onnx


src/onnx_ir/passes/common/onnx_float_16.py

+import numpy.typing as npt
+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper


src/onnx_ir/passes/common/onnx_float_16.py

+import numpy.typing as npt
+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper


src/onnx_ir/passes/common/onnx_float_16.py

+import numpy.typing as npt
+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper


src/onnx_ir/passes/common/onnx_float_16.py

+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper
+from onnx import onnx_pb as onnx_proto


src/onnx_ir/passes/common/onnx_float_16.py

+    np_array = np.where(
+        between(float("-inf"), np_array, -max_finite_val), -max_finite_val, np_array
+    )
+    return np.float16(np_array)  # pyright: ignore[reportReturnType]


src/onnx_ir/passes/common/onnx_float_16.py

+    func_infer_shape = None
+    if not disable_shape_infer and pv.Version(onnx.__version__) >= pv.Version("1.2"):  # pyright: ignore[reportPrivateImportUsage]
+        try:
+            from onnx.shape_inference import infer_shapes


codecov · 2025-06-23T15:31:47Z

Codecov Report

Attention: Patch coverage is 7.69231% with 192 lines in your changes missing coverage. Please review.

Project coverage is 71.66%. Comparing base (e211825) to head (365554f).
Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
src/onnx_ir/passes/common/onnx_float_16.py	7.69%	192 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #86      +/-   ##
==========================================
- Coverage   74.52%   71.66%   -2.87%     
==========================================
  Files          38       39       +1     
  Lines        4687     4895     +208     
  Branches      957     1017      +60     
==========================================
+ Hits         3493     3508      +15     
- Misses        841     1033     +192     
- Partials      353      354       +1

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

src/onnx_ir/passes/common/onnx_float_16.py

+
+import numpy as np
+import numpy.typing as npt
+import onnx


src/onnx_ir/passes/common/onnx_float_16.py

+import numpy.typing as npt
+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper


src/onnx_ir/passes/common/onnx_float_16.py

+import numpy.typing as npt
+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper


src/onnx_ir/passes/common/onnx_float_16.py

+import numpy.typing as npt
+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper


src/onnx_ir/passes/common/onnx_float_16.py

+import onnx
+import packaging.version as pv
+from onnx import helper, numpy_helper
+from onnx import onnx_pb as onnx_proto


src/onnx_ir/passes/common/onnx_float_16.py

+    np_array = np.where(
+        between(float("-inf"), np_array, -max_finite_val), -max_finite_val, np_array
+    )
+    return np.float16(np_array)  # pyright: ignore[reportReturnType]


src/onnx_ir/passes/common/onnx_float_16.py

+    func_infer_shape = None
+    if not disable_shape_infer and pv.Version(onnx.__version__) >= pv.Version("1.2"):  # pyright: ignore[reportPrivateImportUsage]
+        try:
+            from onnx.shape_inference import infer_shapes


bjeffrey92 requested review from titaiwangms and a team as code owners June 17, 2025 12:21

bjeffrey92 force-pushed the port-onnx-float16 branch from 6b1c5e3 to 5d05b60 Compare June 17, 2025 12:23

bjeffrey92 added 3 commits June 20, 2025 12:42

ported module for converting onnx model to mixed pres from onnxconver…

63e08cc

…ter-common Signed-off-by: bjeffrey92 <[email protected]>

abide by all linting rules

9567865

Signed-off-by: bjeffrey92 <[email protected]>

add MIT license information to source code

365554f

Signed-off-by: bjeffrey92 <[email protected]>

bjeffrey92 force-pushed the port-onnx-float16 branch from 5d05b60 to 365554f Compare June 20, 2025 11:42

github-advanced-security bot found potential problems Jun 20, 2025

View reviewed changes

github-advanced-security bot found potential problems Jun 23, 2025

View reviewed changes

Port onnx float16 from onnxconverter-common #86

Are you sure you want to change the base?

Port onnx float16 from onnxconverter-common #86

Uh oh!

Conversation

bjeffrey92 commented Jun 17, 2025

Uh oh!

justinchuby commented Jun 17, 2025

Uh oh!

justinchuby commented Jun 17, 2025

Uh oh!

justinchuby commented Jun 17, 2025

Uh oh!

bjeffrey92 commented Jun 18, 2025

Uh oh!

bjeffrey92 commented Jun 18, 2025

Uh oh!

justinchuby commented Jun 18, 2025

Uh oh!

justinchuby commented Jun 18, 2025

Uh oh!

justinchuby commented Jun 18, 2025

Uh oh!

Check warning

Check warning

Check warning

Check warning

Check warning

Check failure

Check warning

codecov bot commented Jun 23, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Check warning

Check warning

Check warning

Check warning

Check warning

Check failure

Check warning

Uh oh!

codecov bot commented Jun 23, 2025 •

edited

Loading