[Meta] WebNN - Windows ML / ONNX Runtime Issues and Feature Requests
Describe the issue
This is a meta issue to track WebNN / ONNX Runtime relevant open issues.
OT Blocker
ORT Core VF
- https://github.com/microsoft/onnxruntime/pull/29851
- https://github.com/microsoft/onnxruntime/pull/32681
- https://github.com/microsoft/onnxruntime/pull/32679
- https://github.com/microsoft/onnxruntime/pull/32641
- https://github.com/microsoft/onnxruntime/pull/32633
- https://github.com/microsoft/onnxruntime/pull/32611
- https://github.com/microsoft/onnxruntime/pull/32610
- https://github.com/microsoft/onnxruntime/pull/32609
- https://github.com/microsoft/onnxruntime/pull/32607
ORT Core
- https://github.com/microsoft/onnxruntime/issues/29612
- https://github.com/microsoft/onnxruntime/pull/29681 (Impact WebGPU EP, does not impact OV NPU)
- https://github.com/microsoft/onnxruntime/pull/29755
- https://github.com/microsoft/onnxruntime/pull/29799
- https://github.com/microsoft/onnxruntime/pull/28535
- https://github.com/microsoft/onnxruntime/pull/28431
- https://github.com/microsoft/onnxruntime/pull/30889 Fix compiler process cannot load the latest onnxruntime.dll
ORT OpenVINO EP NPU
ORT WebGPU EP // Required PRs for 0.3 branch release
item | unsupported_reason | detail | | -- | -- | -- | -- | -- Add | Missing type: int64 | v14 kernel exists, supports: float,float16,int32,uint32 | ✅ | https://github.com/microsoft/onnxruntime/pull/29844 AveragePool | Unsupported opset: v19 | No compatible kernel version registered | ✅ | https://github.com/microsoft/onnxruntime/pull/29835 Cast | Missing type: uint8 | v21 kernel exists, supports: float16,float,int32,uint32,int64,bool | ✅ | https://github.com/microsoft/onnxruntime/pull/29839 Clip | Missing type: int32 | v13 kernel exists, supports: float | ✅ | https://github.com/microsoft/onnxruntime/pull/29835 Clip | Missing type: int64 | v13 kernel exists, supports: float | ✅ | https://github.com/microsoft/onnxruntime/pull/29834 Expand | Missing type: uint8 | v13 kernel exists, supports: float16,float,int32,uint32,int64,bool | ✅ | https://github.com/microsoft/onnxruntime/pull/29854 Gather | Missing type: uint8 | v13 kernel exists, supports: float,float16,int32,uint32,bool | ✅ | https://github.com/microsoft/onnxruntime/pull/29861 HardSwish | No matching kernel | No compatible kernel version registered | ✅ | https://github.com/microsoft/onnxruntime/pull/29828 Max | No matching kernel | No compatible kernel version registered | ✅ | https://github.com/microsoft/onnxruntime/pull/29833 Min | No matching kernel | No compatible kernel version registered | ✅ | Same PR to Max Reshape | Missing type: int64 | v21 kernel exists, supports: float,float16,int32,uint32 | ✅ | https://github.com/microsoft/onnxruntime/pull/29830 Reshape | Missing type: uint8 | v21 kernel exists, supports: float,float16,int32,uint32 | ✅ | https://github.com/microsoft/onnxruntime/pull/29897 Tile | Missing type: int32 | v13 kernel exists, supports: float,float16 | ✅ | https://github.com/microsoft/onnxruntime/pull/29847 Tile | Missing type: int64 | v13 kernel exists, supports: float,float16 | ✅ | https://github.com/microsoft/onnxruntime/pull/31049 Trilu | No matching kernel | No compatible kernel version registered | ✅ | https://github.com/microsoft/onnxruntime/pull/29845 Concat | Missing type: int64 | supports: float,float16,int32,uint32 | ✅| https://github.com/microsoft/onnxruntime/pull/31049 Gru | Op missing | WebNN noise supression sample | ✅ | https://github.com/microsoft/onnxruntime/pull/29840 CumSum | Missing type: int32 | v14 kernel exists, supports: float,float16 | ✅| https://github.com/microsoft/onnxruntime/pull/31702 Gather | int64 | | ✅ | https://github.com/microsoft/onnxruntime/pull/31714 Clip | | Gate int64 Clip kernel behind enable_int64 flag | ✅ | https://github.com/microsoft/onnxruntime/pull/29918 Min/Max | int64 | | ✅ | https://github.com/microsoft/onnxruntime/pull/31709 Support device-free compile-only sessions | | | ✅ | https://github.com/microsoft/onnxruntime/pull/29681 Robustness provider option | | | ✅ | https://github.com/microsoft/onnxruntime/pull/31971 Zero-initialize writable device allocator buffers | | | ✅ | https://github.com/microsoft/onnxruntime/pull/32063
Chromium
- 8124054 skip SetFakeGdiInit() for the compiler process sandbox
- 8091227 [WebGPU EP] add WebGpuExecutionProvider to
kKnownEPs - 8127421 Disable ORT graph transforms in the GPU process for security
Feature Request
- https://github.com/microsoft/onnxruntime/issues/32496
- https://github.com/microsoft/onnxruntime/issues/28806
- https://github.com/microsoft/onnxruntime/issues/27310
- https://github.com/microsoft/onnxruntime/issues/27181
- https://github.com/microsoft/onnxruntime/issues/27167
- https://github.com/microsoft/onnxruntime/issues/26648
- https://github.com/microsoft/onnxruntime/issues/25302
- https://github.com/microsoft/onnxruntime/issues/23189
- https://github.com/microsoft/onnxruntime/issues/25785
ep:WebGPU
- https://github.com/microsoft/onnxruntime/issues/25236
- https://github.com/microsoft/onnxruntime/issues/32625 (GA blocker, not first OT blocker)
Bug
- https://github.com/microsoft/onnxruntime/issues/29272
- [Blocker][Long Compilation Time] https://github.com/microsoft/onnxruntime/issues/26643
- https://github.com/microsoft/onnxruntime/issues/26618
- https://github.com/microsoft/onnxruntime/issues/26288
ep:WebGPU
- https://github.com/microsoft/onnxruntime/issues/26064
- https://github.com/microsoft/onnxruntime/issues/25914
ep:DML
- https://github.com/microsoft/onnxruntime/issues/26606
- https://github.com/microsoft/onnxruntime/issues/26521
- https://github.com/microsoft/onnxruntime/issues/26525
- https://github.com/microsoft/onnxruntime/issues/26528
- https://github.com/microsoft/onnxruntime/issues/26530
- https://github.com/microsoft/onnxruntime/issues/26532
- https://github.com/microsoft/onnxruntime/issues/26533
- https://github.com/microsoft/onnxruntime/issues/26529
- [Crash] https://github.com/microsoft/onnxruntime/issues/26531
ORT Default CPU
Source: microsoft/onnxruntime