Skip to content

Issues: microsoft/onnxruntime

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

2,287 Open 4,243 Closed
2,287 Open 4,243 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Build] Compile error: "union fp32_bits" defined twice build build issues; typically submitted using template
#22330 opened Oct 6, 2024 by sevagh
[Performance] Python inference runs faster than C++ performance issues related to performance regressions platform:jetson issues related to the NVIDIA Jetson platform
#22328 opened Oct 5, 2024 by ashwin-999
Onnxruntime error during inference with operator (CumSum) converter related to ONNX converters
#22326 opened Oct 5, 2024 by TheMattBin
CUDAExecutionProvider doesn't seem to be used during inference of transformers exported model to ONNX runtime GPU model:transformer issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#22325 opened Oct 4, 2024 by cooper-a
1
[Feature Request] Support for Int64 datatype for shape tensor in Expand Op in ORT-QNN EP ep:QNN issues related to QNN exeution provider feature request request for unsupported feature or enhancement
#22320 opened Oct 4, 2024 by aparmp-quic
[Feature Request] Support for ScatterNd op for QNN-EP ep:QNN issues related to QNN exeution provider feature request request for unsupported feature or enhancement
#22319 opened Oct 4, 2024 by aparmp-quic
[Feature Request] ep:WebGPU ort-web webgpu provider feature request request for unsupported feature or enhancement platform:web issues related to ONNX Runtime web; typically submitted using template
#22317 opened Oct 4, 2024 by load1n9
Build failure on Windows 10 using OpenVino 2024.3 & 2024.4 both. build build issues; typically submitted using template ep:OpenVINO issues related to OpenVINO execution provider platform:windows issues related to the Windows platform
#22314 opened Oct 4, 2024 by prashant-saxena
[Feature request] Deno webgpu support ep:WebGPU ort-web webgpu provider feature request request for unsupported feature or enhancement platform:web issues related to ONNX Runtime web; typically submitted using template
#22309 opened Oct 4, 2024 by jlucaso1
[Web] WebNN optimizations silently failing when using wrong argument names in freeDimensionOverrides ep:WebNN WebNN execution provider platform:web issues related to ONNX Runtime web; typically submitted using template
#22300 opened Oct 3, 2024 by eyaler
[Performance] High CUDA memory usage with ONNX Runtime and inconsistent memory release ep:CUDA issues related to the CUDA execution provider performance issues related to performance regressions
#22297 opened Oct 3, 2024 by niyathimariya
[Feature Request] ORT QNN EP to support ONNX 1.17.0 ep:QNN issues related to QNN exeution provider feature request request for unsupported feature or enhancement
#22293 opened Oct 2, 2024 by liqunfu
1
[Mobile] QNN Execution provider mem alloc failure. api:Java issues related to the Java API ep:QNN issues related to QNN exeution provider platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#22288 opened Oct 1, 2024 by iknowican
2
ORT would be crashed while loading the specific INT4 model ep:DML issues related to the DirectML execution provider
#22284 opened Oct 1, 2024 by peterer0625
[DO NOT UNPIN] Upcoming ORT 1.20 Release Overview
#22274 opened Sep 30, 2024 by sophies927
2
Memory leak after running onnx model numerous times core runtime issues related to core runtime
#22271 opened Sep 30, 2024 by vsbaldeev
1
[Build] [On-device-training] Running onnxruntime-training (CPU) Python Demo on Debian 12 aarch64 Environment build build issues; typically submitted using template ep:RockchipNPU issues related to Rockchip execution provider
#22270 opened Sep 30, 2024 by Leo5050xvjf
Simple FP8 GEMM is not runnable in CPU EP quantization issues related to quantization
#22269 opened Sep 30, 2024 by galagam
[Build] Mismatched library directory in linux-x64 package: lib and lib64 build build issues; typically submitted using template
#22267 opened Sep 30, 2024 by zchrissirhcz
[Feature Request] Add support for building the iOS simulator arm64 version feature request request for unsupported feature or enhancement platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#22257 opened Sep 28, 2024 by cyanic-selkie
2
Ort-Genai benchmark run failed at GroupQueryAttention/RunRotaryEmbedding: Exception thrown at 0x00007FFE7576352C (onnxruntime.dll) in model_benchmark.exe: 0xC0000005: Access violation reading location 0x0000018FE4BB8080.
#22252 opened Sep 27, 2024 by liqunfu
2
[Build] Multiple commands produce "..." build build issues; typically submitted using template platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#22245 opened Sep 27, 2024 by cyanic-selkie
6
[Feature Request] Detect TensorRT cache creation ep:TensorRT issues related to TensorRT execution provider feature request request for unsupported feature or enhancement
#22244 opened Sep 27, 2024 by henryruhs
1
How to determine which provider current inference is using? core runtime issues related to core runtime
#22243 opened Sep 27, 2024 by SolveProb
2
[Performance] fp16 support and performance performance issues related to performance regressions platform:mobile issues related to ONNX Runtime mobile; typically submitted using template
#22242 opened Sep 27, 2024 by cbingdu
3
ProTip! Find all open issues with in progress development work with linked:pr.