Search results

Feature request: add ONNX Runtime GenAI support for Granite Speech models (e.g. granite-4.0-1b-speech-ONNX)

Status: Open.

#2072 In microsoft/onnxruntime-genai;

· KeinNiemand opened on Apr 7, 2026

Feature Request: Support for Google Gemma 4 model family (PLE architecture, variable head dims, KV cache sharing)

Status: Open.

#2062 In microsoft/onnxruntime-genai;

· elbruno opened on Apr 3, 2026

cannot build Qwen/Qwen3-14B on machine with 64GB RAM

Status: Open.

#2047 In microsoft/onnxruntime-genai;

· xiaofeihan1 opened on Mar 26, 2026

"profiling_level": "detailed" is not working for multi models qnn npu

platform:mobile

Status: Open.

#2037 In microsoft/onnxruntime-genai;

· xieofxie opened on Mar 19, 2026

"enable_profiling" in session_options is not working for dml

ep:DML

platform:mobile

Status: Open.

#2031 In microsoft/onnxruntime-genai;

· xieofxie opened on Mar 17, 2026

[Java] onnxruntime-genai-cuda.dll missing from Java JAR and extraction logic in CUDA builds

api:java

ep:CUDA

Status: Open.

#2028 In microsoft/onnxruntime-genai;

· EPNW-Eric opened on Mar 15, 2026

[Bug?] library crash at runtime when loading the model

Status: Open.

#2023 In microsoft/onnxruntime-genai;

· PrestigeDevop opened on Mar 13, 2026

Feature Request: Support for Qwen3.5

Status: Open.

#2016 In microsoft/onnxruntime-genai;

· Fazzioni opened on Mar 10, 2026

[Privacy/Thermal] WorkloadsSessionHost silently consumes 90%+ GPU on Copilot+ PCs without user opt-in

Status: Open.

#2013 In microsoft/onnxruntime-genai;

· RhysBlackbeard opened on Mar 7, 2026

Using Onnxruntime Custom Execution Provider for ORT-GenAI

Status: Open.

#2006 In microsoft/onnxruntime-genai;

· suyash-narain opened on Mar 4, 2026

Config::overlay() on pipeline session_options causes "File doesn't exist" on Model load

Status: Open.

#2004 In microsoft/onnxruntime-genai;

· chenmy77 opened on Mar 4, 2026

Document the config format

Status: Open.

#1990 In microsoft/onnxruntime-genai;

· justinchuby opened on Feb 24, 2026