FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[Original HTTPS Page]
Issues · microsoft/onnxruntime · GitHub
Uh oh!
There was an error while loading.
Please reload this page
.
microsoft
/
onnxruntime
Public
Notifications
You must be signed in to change notification settings
Fork
4.2k
Star
21.7k
Code
Issues
825
Pull requests
822
Discussions
Actions
Projects
Wiki
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security and quality
Insights
Issues
Assigned to me
Created by me
Mentioned
Recent activity
Views
Projects
Milestones
Labels
All issues
Issue creation is restricted in this repository
Issues
Search Issues
is
:
issue
state
:
open
is:issue state:open
Search
Search results
Open
Closed
softmax_warp_forward overflows int32 above 2^31 elements and can return silently wrong results (CUDA and ROCm EPs)
ep:CUDA
issues related to the CUDA execution provider
issues related to the CUDA execution provider
Status: Open.
#32299
In Microsoft/onnxruntime;
·
Jonathan Kirkland (jbk708)
opened
on Aug 27, 2026
XNNPACK EP on Android arm64 aborts the process (Abort message: 'terminating') instead of returning an error — Resize with empty scales, still in 1.26.0
.NET
Pull requests that update .net code
Pull requests that update .net code
api:CSharp
issues related to the C# API
issues related to the C# API
ep:Xnnpack
issues related to XNNPACK EP
issues related to XNNPACK EP
platform:mobile
issues related to ONNX Runtime mobile; typically submitted using template
issues related to ONNX Runtime mobile; typically submitted using template
Status: Open.
#32298
In Microsoft/onnxruntime;
·
andru196
opened
on Aug 27, 2026
[Build] Align CPython 3.14 CUDA 13 wheels with TensorRT 11
ep:CUDA
issues related to the CUDA execution provider
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
issues related to TensorRT execution provider
Status: Open.
#32278
In Microsoft/onnxruntime;
·
Cédric Prezelin (Tenshock)
opened
on Aug 26, 2026
TensorRT EP Resize with +inf input returns NaN while CPU/CUDA EP return +inf
ep:CUDA
issues related to the CUDA execution provider
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
issues related to TensorRT execution provider
Status: Open.
#32258
In Microsoft/onnxruntime;
·
xinxueliu (lackjava-creator)
opened
on Aug 25, 2026
CUDA EP ReduceMax/ReduceMin return finite limits instead of +/-inf for all-infinite inputs
ep:CUDA
issues related to the CUDA execution provider
issues related to the CUDA execution provider
Status: Open.
#32256
In Microsoft/onnxruntime;
·
xinxueliu (lackjava-creator)
opened
on Aug 25, 2026
[Performance] ORT 1.29 CPU FP16 Gemm is ~3500x slower than 1.28 on Windows x64
api:CSharp
issues related to the C# API
issues related to the C# API
performance
issues related to performance regressions
issues related to performance regressions
platform:windows
issues related to the Windows platform
issues related to the Windows platform
Status: Open.
#32255
In Microsoft/onnxruntime;
·
WithSalt (withsalt)
opened
on Aug 25, 2026
TensorRT EP engine cache reuses engine for same graph name with different static input shape
ep:TensorRT
issues related to TensorRT execution provider
issues related to TensorRT execution provider
Status: Open.
#32254
In Microsoft/onnxruntime;
·
xinxueliu (lackjava-creator)
opened
on Aug 25, 2026
cuda graph bug for recurrent state inplace update
ep:CUDA
issues related to the CUDA execution provider
issues related to the CUDA execution provider
Status: Open.
#32243
In Microsoft/onnxruntime;
·
Tianlei Wu (tianleiwu)
opened
on Aug 24, 2026
[Web] Deprecate the onnxruntime-web WebGL backend
ep:WebGPU
ort-web webgpu provider
ort-web webgpu provider
platform:web
issues related to ONNX Runtime web; typically submitted using template
issues related to ONNX Runtime web; typically submitted using template
Status: Open.
#32241
In Microsoft/onnxruntime;
·
Edward Chen (edgchen1)
opened
on Aug 24, 2026
[Build] onnxruntime-node install fails: "Failed to download build list. HTTP status code = 302" (script doesn't follow redirects)
.NET
Pull requests that update .net code
Pull requests that update .net code
build
build issues; typically submitted using template
build issues; typically submitted using template
platform:web
issues related to ONNX Runtime web; typically submitted using template
issues related to ONNX Runtime web; typically submitted using template
Status: Open.
#32233
In Microsoft/onnxruntime;
·
whale (is-whale)
opened
on Aug 24, 2026
[Feature Request] WebGPU LinearAttention state_window for speculative/MTP rollback
ep:WebGPU
ort-web webgpu provider
ort-web webgpu provider
platform:web
issues related to ONNX Runtime web; typically submitted using template
issues related to ONNX Runtime web; typically submitted using template
Status: Open.
#32232
In Microsoft/onnxruntime;
·
Fu Xiaonan (FU-max-boop)
opened
on Aug 24, 2026
[Bug] GemmTransposeFusion folds an identity Transpose (perm=[0,1]) into Gemm transA/transB, producing silently wrong results
ep:CoreML
issues related to CoreML execution provider
issues related to CoreML execution provider
Status: Open.
#32228
In Microsoft/onnxruntime;
·
xinxueliu (lackjava-creator)
opened
on Aug 24, 2026
Back
|
FazBrowse Home
|
New Git URL