Comments (4)
Not at this time. We welcome contributions.
from onnxruntime.
The existing arm cross-compile flow gets you 95% of the way there. The only major changes to be made are substituting the SIMD mlas functions with scalar equivalents. Ideally you'd make use of the v-extension but that's still a wip.
For other architectures, so long as your target platform has a c++ compiler it should just compile fine, although you'll probably want to create your own provider backend to take advantage of vectorization.
I'm maintaining a fork that works on riscv. It also supports the gemmini matmul accelerator (a rocc co-processor).
from onnxruntime.
This issue has been automatically marked as stale due to inactivity and will be closed in 7 days if no further activity occurs. If further support is needed, please provide an update and/or more details.
from onnxruntime.
This issue has been automatically closed due to inactivity. Please reactivate if further support is needed.
from onnxruntime.
Related Issues (20)
- Failing to run Dockerfile of ONNXRuntime with TensorRT integration[Build] HOT 4
- [Training] How to change onnx model structure at runtime in C++?
- [Build] CudaKernelTest.InvertibleLayerNormGrad_MidSizeTensor Test Failure in Windows GPU CI Pipeline
- CoreDump bad_alloc while GetShape HOT 3
- Running inpainting model with integrated graphics card Intel HD Graphics 630 using Microsoft.ML.OnnxRuntime 1.17.1 + DML execution provider HOT 1
- [bug] `quantize_dynamic` results in `AttributeError: 'NoneType' object has no attribute 'HasField'` HOT 3
- Windows 11 Runtime Issue HOT 5
- [Feature Request] HOT 3
- [Build & Implementation] An EP depends on a couple of other EPs. Undefined symbol resolution. HOT 3
- RUNTIME_EXCEPTION : Non-zero status code returned while running Reshape node HOT 3
- Shared Arena Env Allocator Usage Across Modules HOT 5
- Some problems about the onnx-tensorrt source code. HOT 6
- [Build] Encountered error executing OPs on RISCV platform HOT 1
- [Build] add_library cannot create ALIAS target "nsync::nsync_cpp" because target "nsync_cpp" does not already exist HOT 3
- [Build] Trying to use TensorrtExecutionProvider. Model not loading HOT 8
- Failed to allocated memory for requested buffer of size X HOT 5
- Inference session crashes using ONNX runtime. HOT 4
- [Mobile] HOT 2
- [Web] can not install 1.17.1 for nodejs HOT 1
- Onnx Runtime EntryPointNotFoundException: OrtGetApiBase in Unity Application. HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnxruntime.