-
Notifications
You must be signed in to change notification settings - Fork 3.7k
Insights: onnx/onnx
Overview
-
- 7 Merged pull requests
- 0 Open pull requests
- 4 Closed issues
- 4 New issues
Could not load contribution data
Please try again later
7 Pull requests merged by 4 people
-
Bump docker/setup-qemu-action from 3.0.0 to 3.2.0
#6270 merged
Nov 23, 2024 -
Remove/raise exception when external file exists during onnx.save
#6497 merged
Nov 21, 2024 -
Publish to test.pypi only for testing (with workflow dispatch)
#6548 merged
Nov 21, 2024 -
Removing unit test involving onnxruntime
#6549 merged
Nov 21, 2024 -
Fix of the devbuild publish-workflow
#6546 merged
Nov 18, 2024 -
Fix extra-semi warnings on public headers
#6538 merged
Nov 18, 2024 -
Simplify CMake argument handling in setup.py
#6545 merged
Nov 17, 2024
4 Issues closed by 2 people
-
Objective of test: "Verify ONNX with ONNX Runtime PyPI package"?
#6484 closed
Nov 21, 2024 -
Python 3.13 support
#6339 closed
Nov 21, 2024 -
Docs pages build pipeline is red
#6507 closed
Nov 19, 2024 -
Onnx-Weekly upload to pypi failed: 413 Request Entity Too Large
#6499 closed
Nov 18, 2024
4 Issues opened by 4 people
-
Make InstanceNormalization weights and bias optional
#6552 opened
Nov 23, 2024 -
invalid version error when converting llama3 model from opset 20 to 21
#6551 opened
Nov 23, 2024 -
Is it possible to customize wrapPerspective operator in Opencv with Onnx?
#6550 opened
Nov 21, 2024 -
[Feature request] ONNX need support opset MatMulInteger input 4bit
#6547 opened
Nov 19, 2024
12 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
Add MatMulNBits Operator
#6500 commented on
Nov 21, 2024 • 4 new comments -
Allow scale type in QuantizeLinear and DequantizeLinear to be different from the high-precision type
#6531 commented on
Nov 22, 2024 • 4 new comments -
Way to swap parameters inside .onnx graph (LoRA functionality)
#6144 commented on
Nov 18, 2024 • 0 new comments -
Build Error: Protobuf pinned version missing `<cstdint>` definition on its headers
#6295 commented on
Nov 18, 2024 • 0 new comments -
How to use version converter on a large (>2GB) model?
#6529 commented on
Nov 19, 2024 • 0 new comments -
[1.16.2/1.17?] ONNX build Windows
#6267 commented on
Nov 20, 2024 • 0 new comments -
torch.fft.rfftn,torch.fft.irfftn are not supported in ONNX opset version 17
#4845 commented on
Nov 22, 2024 • 0 new comments -
Shape inference fails on Concat when first tensor is initialized empty
#6276 commented on
Nov 23, 2024 • 0 new comments -
[Feature request] Standardize error handling
#5573 commented on
Nov 23, 2024 • 0 new comments -
Breaking change in `load_model` from `1.14.1` -> `1.15.0`
#5746 commented on
Nov 23, 2024 • 0 new comments -
Unify the behavior of infer_shapes and check_model
#6479 commented on
Nov 21, 2024 • 0 new comments -
Add protobuf local build option
#6495 commented on
Nov 17, 2024 • 0 new comments