-
Notifications
You must be signed in to change notification settings - Fork 2.8k
Issues: microsoft/onnxruntime
[Performance] Mapfile support for certain external data files...
#21195
opened Jun 27, 2024 by
ivberg
Open
2
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
[Training] Cannot export model for inferencing from session created from buffers
training
issues related to ONNX Runtime training; typically submitted using template
#21152
opened Jun 24, 2024 by
riccardopinosio
[Performance] Whisper model inference results incorrect after Transformer Optimizer
ep:DML
issues related to the DirectML execution provider
platform:windows
issues related to the Windows platform
quantization
issues related to quantization
#21150
opened Jun 24, 2024 by
XciciciX
[Training] Onnxruntime-training 1.18.0 for windows not available
platform:windows
issues related to the Windows platform
stale
issues that have not been addressed in a while; categorized by a bot
training
issues related to ONNX Runtime training; typically submitted using template
#21149
opened Jun 24, 2024 by
GeorgeS2019
[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
#21148
opened Jun 23, 2024 by
11721206
[Jvm] Native crash during createSession: std::bad_cast
api:Java
issues related to the Java API
#21147
opened Jun 23, 2024 by
gtf35
[Build] build python wheel fails
build
build issues; typically submitted using template
#21145
opened Jun 22, 2024 by
DaniAffCH
Quantized ONNX Model Still Has Float32 Input/Output Tensors
quantization
issues related to quantization
stale
issues that have not been addressed in a while; categorized by a bot
#21138
opened Jun 21, 2024 by
jenchun-potentialmotors
How to convert quantized ONNX model from Tensor-Oriented format to Operator-Oriented format?
quantization
issues related to quantization
stale
issues that have not been addressed in a while; categorized by a bot
#21137
opened Jun 21, 2024 by
hoangtv2000
Symbolic Shape infer fails on onnx file without much logs
ep:TensorRT
issues related to TensorRT execution provider
stale
issues that have not been addressed in a while; categorized by a bot
#21120
opened Jun 20, 2024 by
aaditya-srivathsan
[Feature Request] Support for Florence-2 model family
feature request
request for unsupported feature or enhancement
model:transformer
issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
#21118
opened Jun 20, 2024 by
theolivenbaum
cannot resolve operator 'Cast' with opsets: ai.onnx v17 [Web]
platform:web
issues related to ONNX Runtime web; typically submitted using template
stale
issues that have not been addressed in a while; categorized by a bot
#21115
opened Jun 20, 2024 by
SpadgerBoy
[Bug] fp8 quantization, weight_error is empty, but qdq_err is normal
quantization
issues related to quantization
stale
issues that have not been addressed in a while; categorized by a bot
#21113
opened Jun 20, 2024 by
zccyman
[Web] ort-web webgpu provider
model:transformer
issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
platform:web
issues related to ONNX Runtime web; typically submitted using template
Error: [WebGPU] Kernel "[Conv] /text_encoder/encoder/layers.0/feed_forward/conv_2/Conv" failed. Error: FILTER_IN_CHANNEL should be equal to DATA_CHANNEL
ep:WebGPU
#21108
opened Jun 19, 2024 by
xenova
[Performance] Running YOLOv8-seg.onnx with Dynamic Batch Size on GPU
api:Javascript
issues related to the Javascript API
ep:WebGPU
ort-web webgpu provider
performance
issues related to performance regressions
platform:web
issues related to ONNX Runtime web; typically submitted using template
#21103
opened Jun 19, 2024 by
shimaamorsy
DML cannot use device_id = 1 , run_with_iobinding failed.
ep:DML
issues related to the DirectML execution provider
platform:windows
issues related to the Windows platform
#21092
opened Jun 19, 2024 by
Jay19751103
[Feature Request] support FP8 calibraion method and quantization
feature request
request for unsupported feature or enhancement
quantization
issues related to quantization
#21090
opened Jun 19, 2024 by
zccyman
[Bug] W16A16 quantization, qdq_error is empty, but W8A8 is normal
quantization
issues related to quantization
stale
issues that have not been addressed in a while; categorized by a bot
#21089
opened Jun 19, 2024 by
zccyman
[Mobile] Segmentation fault after repeated inference
platform:mobile
issues related to ONNX Runtime mobile; typically submitted using template
#21082
opened Jun 18, 2024 by
laurenspriem
Segmentation fault during inference
core runtime
issues related to core runtime
stale
issues that have not been addressed in a while; categorized by a bot
#21069
opened Jun 17, 2024 by
bwtlt
[Training] Support for RKNPU Execution Provider on RK3562 Platform and On-Device Training Capabilities
ep:RockchipNPU
issues related to Rockchip execution provider
stale
issues that have not been addressed in a while; categorized by a bot
training
issues related to ONNX Runtime training; typically submitted using template
#21060
opened Jun 16, 2024 by
Leo5050xvjf
Flan-T5 small converted model produces wrong result with batch size > 1 and long senetences
model:transformer
issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
stale
issues that have not been addressed in a while; categorized by a bot
#21053
opened Jun 15, 2024 by
PKaralupov
onnxruntime shape mismatch during quantization of yolov8 models
quantization
issues related to quantization
#21048
opened Jun 14, 2024 by
Jamil
[Documentation] Install page missing instructions for onnxruntime-rocm
documentation
improvements or additions to documentation; typically submitted using template
ep:ROCm
questions/issues related to ROCm execution provider
#21036
opened Jun 13, 2024 by
shaunclimbon
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
ProTip!
Adding no:label will show everything without a label.