TornadoVM VS onnxruntime

You don't need to use C++ to interface with CUDA or even write it.

A while ago NVIDIA and the GraalVM team demoed grCUDA which makes it easy to share memory with CUDA kernels and invoke them from any managed language that runs on GraalVM (which includes JIT compiled Python). Because it's integrated with the compiler the invocation overhead is low:

https://developer.nvidia.com/blog/grcuda-a-polyglot-language...

And TornadoVM lets you write kernels in JVM langs that are compiled through to CUDA:

https://www.tornadovm.org

There are similar technologies for other languages/runtimes too. So I don't think that will cause NVIDIA to lose ground.

Presented by Juan Fumero, PhD & Research Fellow (The University of Manchester, UK) during the JVM Language Summit 2023 (Santa Clara CA).

More information on TornadoVM can be found at https://www.tornadovm.org/

Tags: #Java #JVMLS #GPU #FPGA #OpenJDK #GraalVM #AI

ONNX Runtime: ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Embedding generation uses the ONNX runtime under the hood. This is a cross-platform inferencing library that supports multiple execution providers from CPU to specialized GPUs.

tfjs is dead, looking at the commit history. The standard now is to convert PyTorch to onnx, then use onnxruntime (https://github.com/microsoft/onnxruntime/tree/main/js/web) to run the model on the browsdr.

- slang[2] has the potential, but the meta programming part is not as strong as C++, existing libraries cannot be used.

The above conclusion is drawn from my work https://github.com/microsoft/onnxruntime/tree/dev/opencl, purely nightmare to work with thoes drivers and jit compilers. Hopefully Vcc can take compute shader more seriously.

[1]: https://www.circle-lang.org/

I did. It depends what you want, for an overview of how ONNX Runtime works then Microsoft have a bunch of things on https://onnxruntime.ai, but the Java content is a bit lacking on there as I've not had time to write much. Eventually I'll probably write something similar to the C# SD tutorial they have on there but for the Java API.

For writing ONNX models from Java we added an ONNX export system to Tribuo in 2022 which can be used by anything on the JVM to export ONNX models in an easier way than writing a protobuf directly. Tribuo doesn't have full coverage of the ONNX spec, but we're happy to accept PRs to expand it, otherwise it'll fill out as we need it.

What about models besides GPT? Most of the popular vector encoding models aren't using this architecture.

If you really didn't want PyTorch/Transformers, you could consider exporting your models to ONNX (https://github.com/microsoft/onnxruntime).