- Notifications
You must be signed in to change notification settings - Fork0
Releases: sdpython/onnx-array-api
Releases · sdpython/onnx-array-api
0.3.1
96eb50e
This commit was created on GitHub.com and signed with GitHub’sverified signature.
Compare
Could not load tags
Nothing to show
{{ refName }}defaultLoading
0.3.0
689cc6f
This commit was created on GitHub.com and signed with GitHub’sverified signature.
Compare
Could not load tags
Nothing to show
{{ refName }}defaultLoading
Assets2
Uh oh!
There was an error while loading.Please reload this page.
0.2.0
492b6d4
This commit was created on GitHub.com and signed with GitHub’sverified signature.
Compare
Could not load tags
Nothing to show
{{ refName }}defaultLoading
- #77: supports ConcatOfShape and Slice with the light API
- #76,#79: add a mode to compare models without execution
- #75: add QuickGelu to ExtendedReferenceEvaluator
- #71: adds tools to compare two onnx graphs
- #61: adds function to plot onnx model as graphs
- #60: supports translation of local functions
- #59: add methods to update nodes in GraphAPI
Assets2
Uh oh!
There was an error while loading.Please reload this page.
0.1.3
8b54ad1
This commit was created on GitHub.com and signed with GitHub’sverified signature. The key has expired.
Compare
Could not load tags
Nothing to show
{{ refName }}defaultLoading
Assets2
Uh oh!
There was an error while loading.Please reload this page.
0.1.2
70d6f64
This commit was created on GitHub.com and signed with GitHub’sverified signature. The key has expired.
Compare
Could not load tags
Nothing to show
{{ refName }}defaultLoading
- #42: first sketch for a very simple API to create onnx graph in one or two lines
- #27: add function from_array_extended to convert
an array to a TensorProto, including bfloat16 and float 8 types - #24: add ExtendedReferenceEvaluator to support scenario
for the Array API onnx does not support - #22: support OrtValue in functionort_profile
- #17: implements ArrayAPI
- #3: fixes Array API with onnxruntime and scikit-learn
Assets2
Uh oh!
There was an error while loading.Please reload this page.