server VS onnx-tensorrt

As always, it depends a lot on what you're doing, and a lot of people are using Python for AI.

One of the drawbacks of multi-processing versus multi-threading is that you cannot share memory (easily, cheaply) between processes. During model training, and even during inference, this becomes a problem.

For example, imagine a high volume, low latency, synchronous computer vision inference service. If you're handling each request in a different process, then you're going to have to jump through a bunch of hoops to make this performant. For example, you'll need to use shared memory to move data around, because images are large, and sockets are slow. Another issue is that each process will need a different copy of the model in GPU memory, which is a problem in a world where GPU memory is at a premium. You could of course have a single process for the GPU processing part of your model, and then automatically batch inputs into this process, etc. etc. (and people do) but all this is just to work around the lack of proper threading support in Python.

By the way, if anyone is struggling with these challenges today, I recommend taking a peek at nvidia's [triton](https://github.com/triton-inference-server/server) inference server, which handles a lot of these details for you. It supports things like zero-copy sharing of tensors between parts of your model running in different processes/threads and does auto-batching between requests as well. Especially auto-batching gave us big throughput increase with a minor latency penalty!

I am wondering what is the best / most cost-efficient way to serve llama V2. - llama.cpp (is it production ready or just for playing around?) ? - Triton inference server ? - HF text generation inference ?

For inference of CNNs, memory should really not be an issue. If it is a software engineering problem, not a hardware issue. FP16 or Int8 for weights is fine and weight size won’t increase due to the high resolution. And during inference memory used for hidden layer tensors can be reused as soon as the last consumer layer has been processed. You likely using something that is designed for training for inference and that blows up the memory requirement, or if you are using TensorRT or something like that, you need to be careful to avoid that every tasks loads their own copy of the library code into the GPU. Maybe look at https://github.com/triton-inference-server/server

I am looking for something like [Triton Inference Server](https://github.com/triton-inference-server/server) or [TFX Serving](https://www.tensorflow.org/tfx/guide/serving), but in Rust. I came across [Orkon](https://github.com/vertexclique/orkhon) which seems to be dormant and a bunch of examples off of the [Awesome-Rust-MachineLearning](https://github.com/vaaaaanquish/Awesome-Rust-MachineLearning)

You've already mentioned Seldon Core which is well worth looking at but if you're just after the raw multi-model serving aspect rather than a fully-fledged deployment framework you should maybe take a look at the individual inference servers: Triton Inference Server and MLServer both support multi-model serving for a wide variety of frameworks (and custom python models). MLServer might be a better option as it has an MLFlow runtime but only you will be able to decide that. There also might be other inference servers that do MMS that I'm not aware of.

[1] - We use onnx-tensorrt for this TensorRT compatibility checks.

Conversion was done from Keras Tensorflow using to ONNX https://github.com/onnx/keras-onnx followed by ONNX to TensorRT using https://github.com/onnx/onnx-tensorrt The Python code used for inference using TensorRT can be found at https://github.com/jonnor/modeld/blob/tensorrt/tensorrtutils.py

Hi! You can run the models trained in Lobe on the Jetson Nano, either through TensorFlow (https://docs.nvidia.com/deeplearning/frameworks/install-tf-jetson-platform/index.html), ONNX runtime (https://elinux.org/Jetson_Zoo#ONNX_Runtime), or running ONNX on TensorRT (https://github.com/onnx/onnx-tensorrt).

Hello, I would like to install https://github.com/onnx/onnx-tensorrt from a package because compiling is a lot of complicated. Is there any source for this package?