FasterTransformer VS onnxruntime

https://docs.nvidia.com/ai-enterprise/overview/0.1.0/platfor...

RIVA: NVIDIA® Riva, a premium edition of NVIDIA AI Enterprise software, is a GPU-accelerated speech and translation AI SDK

FasterTransformer: https://github.com/NVIDIA/FasterTransformer an

There could be some spectrum of this expertise. For instance, https://github.com/NVIDIA/FasterTransformer, https://github.com/microsoft/DeepSpeed

Have anyone tried to optimize the forward and backward using custom Cuda code or fused kernel to speed up the training time of current LLMs? I only have seen FasterTransformer ( NVIDIA/FasterTransformer) and other similar tools but they're only focusing on inference.

Replit built Ghostwriter on the open source scene based on Salesforce’s Codegen, using Nvidia’s FasterTransformer and Triton server for highly optimized decoders, and the knowledge distillation process of the CodeGen model from two billion parameters to a faster model of one billion parameters.

Nvidia FasterTransformer is a mix of Pytorch and CUDA/C++ dedicated code. The performance boost is huge on T5, they report a 10X speedup like TensorRT. However, the speedup is computed on a translation task where sequences are 25 tokens long on average. In our experience, improvement on very short sequences tend to decrease by large margins on longer ones. Still we plan to dig deeper into this project as it implements very interesting ideas.

On the other side of the spectrum, there is Nvidia demos (here or there) showing us how to build manually a full Transformer graph (operator by operator) in TensorRT to get best performance from their hardware. It’s out of reach for many NLP practitioners and it’s time consuming to debug/maintain/adapt to a slightly different architecture (I tried). Plus, there is a secret: the very optimized model only works for specific sequence lengths and batch sizes. Truth is that, so far (and it will improve soon), it’s mainly for MLPerf benchmark (the one used to compare DL hardware), marketing content, and very specialized engineers.

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).