-
Notifications
You must be signed in to change notification settings - Fork 2.9k
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[TensorRT ExecutionProvider] Cannot infer the model on a GPU device with an ID other than 0
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
#21276
opened Jul 8, 2024 by
dat58
CUDA_PATH is set but CUDA wasnt able to be loaded
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#21272
opened Jul 6, 2024 by
TeKett
[Feature Request] Support linux/arm64 wheels for onnxruntime-gpu
ep:CUDA
issues related to the CUDA execution provider
feature request
request for unsupported feature or enhancement
platform:jetson
issues related to the NVIDIA Jetson platform
#21232
opened Jul 2, 2024 by
gowthamravichandran
Inference result different between cuda and cpu
ep:CUDA
issues related to the CUDA execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#21220
opened Jul 1, 2024 by
CapJunkrat
[Documentation] How Configure CUDA 12.* and cuDNN for GPU with ONNX Runtime and C# on Windows 11
api:CSharp
issues related to the C# API
documentation
improvements or additions to documentation; typically submitted using template
ep:CUDA
issues related to the CUDA execution provider
platform:windows
issues related to the Windows platform
#21212
opened Jun 29, 2024 by
GeorgeS2019
[Documentation] Setup the CUDA Environment is not detailed enough
documentation
improvements or additions to documentation; typically submitted using template
ep:CUDA
issues related to the CUDA execution provider
platform:windows
issues related to the Windows platform
stale
issues that have not been addressed in a while; categorized by a bot
#21197
opened Jun 27, 2024 by
BrainSlugs83
ORT 1.18.1 Release Candidates available for testing
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
platform:windows
issues related to the Windows platform
release:1.18.1
#21173
opened Jun 25, 2024 by
yf711
[Feature Request] Add DFT support for CUDAExecutionProvider
ep:CUDA
issues related to the CUDA execution provider
feature request
request for unsupported feature or enhancement
#21164
opened Jun 25, 2024 by
alexander-veselov
[Performance] CUDA kernel not found in registries for Op type: ScatterND
ep:CUDA
issues related to the CUDA execution provider
performance
issues related to performance regressions
stale
issues that have not been addressed in a while; categorized by a bot
#21148
opened Jun 23, 2024 by
11721206
Non-zero status code returned while running ConvTranspose node.
ep:CUDA
issues related to the CUDA execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#21034
opened Jun 13, 2024 by
Jerry-Master
Mismatch in results for TensorRT session and cuda Session
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
model:transformer
issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#20986
opened Jun 10, 2024 by
akmalmasud96
[Performance] Severe performance penalty with transformer model and DirectML
ep:CUDA
issues related to the CUDA execution provider
ep:DML
issues related to the DirectML execution provider
performance
issues related to performance regressions
platform:windows
issues related to the Windows platform
#20983
opened Jun 10, 2024 by
andrea-cimatoribus-pix4d
[Build] TensorRT 10 nvinfer1 APIs deprecated
build
build issues; typically submitted using template
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
#20923
opened Jun 4, 2024 by
tianleiwu
Gemm fp8 run error
ep:CUDA
issues related to the CUDA execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#20869
opened May 30, 2024 by
KnightYao
Error in quantize vicuna-7b model from fp16 to int8
ep:CUDA
issues related to the CUDA execution provider
quantization
issues related to quantization
stale
issues that have not been addressed in a while; categorized by a bot
#20867
opened May 30, 2024 by
JackWeiw
[Build] Dockerfile.tensorrt out of date
build
build issues; typically submitted using template
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
#20840
opened May 28, 2024 by
tianleiwu
How can I debug a reproducible error?
ep:CUDA
issues related to the CUDA execution provider
model:transformer
issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
platform:windows
issues related to the Windows platform
stale
issues that have not been addressed in a while; categorized by a bot
#20792
opened May 23, 2024 by
MithrilMan
[Build] MoE related unit tests fail for older architectures such as Pascal when building dev debug
ep:CUDA
issues related to the CUDA execution provider
platform:windows
issues related to the Windows platform
#20788
opened May 23, 2024 by
yuslepukhin
[Documentation Request] Required cuDNN version for OnnxRuntime 1.18
documentation
improvements or additions to documentation; typically submitted using template
ep:CUDA
issues related to the CUDA execution provider
ep:TensorRT
issues related to TensorRT execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#20784
opened May 23, 2024 by
nrudakov
[Feature Request] Get device ids via get_available_device_ids()
ep:CUDA
issues related to the CUDA execution provider
ep:OpenVINO
issues related to OpenVINO execution provider
ep:ROCm
questions/issues related to ROCm execution provider
feature request
request for unsupported feature or enhancement
#20725
opened May 18, 2024 by
henryruhs
[Build] 0.18.0 release breaks Hummingbird build pipeline
build
build issues; typically submitted using template
ep:CUDA
issues related to the CUDA execution provider
ep:MIGraphX
issues related to AMD MI GraphX execution provider
ep:ROCm
questions/issues related to ROCm execution provider
ep:TensorRT
issues related to TensorRT execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#20715
opened May 17, 2024 by
ksaur
cuda's FusedConv is not support Sigmod
ep:CUDA
issues related to the CUDA execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#20708
opened May 17, 2024 by
marktohark
User-provided session logging function is not used for every log
ep:CUDA
issues related to the CUDA execution provider
ep:DML
issues related to the DirectML execution provider
ep:TensorRT
issues related to TensorRT execution provider
platform:windows
issues related to the Windows platform
#20680
opened May 14, 2024 by
JulienTheron
ProTip!
What’s not been updated in a month: updated:<2024-08-29.