issues Search Results · repo:microsoft/onnxruntime-genai language:C++
Filter by
412 results
(110 ms)412 results
inmicrosoft/onnxruntime-genai (press backspace or delete to remove)I have found that openvino relate code has been merged into main branch in latest commit history. I wonder how can I
infer with openvino EP. If you can provide the openvino detail self build and infer ...
ep:DML
ZhangWei125521
- Opened 2 days ago
- #1501
Hello,
I am trying to build onnxruntime-genai for iOS using this tutorial
https://github.com/Azure-Samples/Phi-3MiniSamples/blob/main/ios/README.md. But i think it is now out of date as the is
no branch ...
platform:mobile
sahmed53
- Opened 9 days ago
- #1484
Since the GeneratorParams.input_ids attribute has been decommissioned in the latest version of OGA, what is the
alternative?
input_tokens = test_enc[(i * seqlen) : ((i + 1) * seqlen - 1)] params.input_ids ...
satreysa
- 2
- Opened 16 days ago
- #1458
Describe the bug Phi-4-multimodal-onnx audio task prompt |user| |audio_1| Transcribe the audio clip into text. |end|
|assistant| responses with this instead of the text transcription:
I m sorry, but I ...
Savvkin
- Opened 17 days ago
- #1455
I m experiencing problems using the Phi-4-mini-instruct model where it will generate responses that begin to repeat text
until max_length is reached.
To Reproduce I see this problem with my application, ...
f2bo
- 9
- Opened 18 days ago
- #1450
If you have any plan to enable Qwen3-30B-A3B which architectures is Qwen3MoeForCausalLM
ZhangWei125521
- 1
- Opened 24 days ago
- #1433
Describe the bug
I have encountered the following OGA error message:
Completion failure max_length (2347) cannot be greater than model context_length (2176)
I am mainly trying to understand OGA s definition ...
jeremyfowers
- 2
- Opened 29 days ago
- #1425
Hi all, I’ve optimized the finetuned Phi-4 MM Instruct vision model by converting it to ONNX and applying quantization —
inference time dropped from 26s ➝ 7s. :tada:
I have a few quick questions:
Audio ...
MeemankGupta
- Opened on Apr 24
- #1423
Describe the bug Windows on ARM users commonly use AMD64 python to execute models using ONNX runtime. This is needed
because several python packages (eg. Torch, h5py, etc.) do not yet ship ARM64 for Windows ...
platform:windows
kory
- 14
- Opened on Apr 23
- #1417
The model builder currently uses opset 14 and IR version 7 for built models. I recommend adopting a later opset (18+)
and IR version (10) for the models to leverage latest onnx features and help the ecosystem ...
justinchuby
- Opened on Apr 23
- #1414

Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.