microsoft/onnxruntime-inference-examples
Examples for using ONNX Runtime for machine learning inferencing.
C++MIT
Issues
- 1
OnnxRuntime does not work when running on real iPhone - The type initializer for 'Microsoft.ML.OnnxRuntime.NativeMethods' threw an exception.
#455 opened by codingzerotohero - 1
Android - App crash when using Phi-3
#444 opened by XantaKross - 0
- 0
Issue: Error Loading 8 bit quntized ONNX Model on inference- Protobuf Parsing Failed
#453 opened by chakka12345677 - 0
Try to convert the original phi-3-mini-4k and put it in the provided APP, but get the exception.
#452 opened by scchiustone - 0
- 0
issue in quantised model generated response
#450 opened by ragesh2000 - 3
speed up phi-3 inference?
#428 opened by CHNtentes - 0
Cannot convert Llama-3-awq to ONNX
#448 opened by Toan-it-mta - 1
RUNTIME_EXCEPTION : Non-zero status code returned while running Mul node. Name:'/time_proj/Mul' Status Message: /onnxruntime_src/onnxruntime/core/providers/cpu/math/element_wise_ops.h:540 void onnxruntime::BroadcastIterator::Init(ptrdiff_t, ptrdiff_t) axis == 1 || axis == largest was false. Attempting to broadcast an axis by a dimension other than 1. 2 by 160
#367 opened by siddharth062022 - 2
onnxruntime.capi.onnxruntime_pybind11_state.RuntimeException: [ONNXRuntimeError] : 6 : RUNTIME_EXCEPTION : Non-zero status code returned while running ReduceMax node. Name:'488_ReduceMax' Status Message:
#447 opened by fanshao123456 - 1
- 0
[New Project] Inference of Stable-Diffisuion on All Platform with ONNXRuntime
#446 opened by Windsander - 0
phi-3 vision onnxruntime on android
#445 opened by henrywang0314 - 4
Fail to Build Phi-3 in android
#442 opened by Vinaysukhesh98 - 0
Failed running on iPhone (14 Pro Max)
#443 opened by privateLLM2024 - 1
- 2
- 7
- 3
QNN C++ Example not working on Surface Pro 9
#404 opened by hschumanncvx - 1
- 0
The onnx model can't be loaded on the front end, which uses the react architecture
#427 opened by tanggang1997 - 1
Output image is weired while trying to inference esrgan, Someone help me please.
#423 opened by md-rifatkhan - 1
exporting the vit_b model with sam exporter ?
#422 opened by flores-o - 0
- 0
- 1
Quantization Onnx - AssertionError
#377 opened by katia-katkat - 0
model is taken from the source: Yolov8 in extensions and with support for pre/postprocessing does not detect objects.
#416 opened by Pesekot1 - 3
Fail to quantize the Llama-2-7b-chat-hf model
#375 opened by igaspard - 4
error "QNN execution provider is not supported in this build" when testing ONNX QNN EP
#397 opened by shawnyxf - 2
- 1
- 0
InferenceSession on GPU
#411 opened by shimaamorsy - 1
- 1
About inference efficiency of ONNX with QNN EQ
#402 opened by shawnyxf - 0
c_cxx/customop seems code can't work in linux
#408 opened by viking714 - 9
- 2
Incorrect Responses for Llama-2-7b-hf with RTN/GPTQ INT4 Asymmetric Quantization
#381 opened by VishalX - 1
android app example with whisper_base_cpu_int8.onnx gives out of memory error
#382 opened by suyash-narain - 6
Running QNN C++ example with other models
#376 opened by hhschumann - 0
how to obtain and postprocess the output tensor after inference of onnx model in c++
#372 opened by ZZJzhou - 0
- 2
- 0
- 2
no available backend found. ERR: [wasm] TypeError: _ is not a function [cpu] Error: previous call to 'initializeWebAssembly()'
#358 opened by peng20017 - 0
ValueError: Expected InsertedCast_gfpgan.conv_body_first.weight to be an initializer
#363 opened by AdvancedHe - 0
Segment Anything example fails with "invalid rank for input" on Mac with Chrome
#364 opened by mprynce - 7
- 0
- 0
how to set decoder_input_ids
#353 opened by zanyar8519