Marco Giovanni Bignotti

Question: Feature extraction on time series batch

12

Hello, First of all, I would like to thank you for the really nice library. I think it is much more straight forward and at the same time flexible, compared...

Add Polars Support

4

**Is your feature request related to a problem? Please describe.** Qdrant has different search APIs (e.g. search, search batch, recommend,...), which is very cool. However, the data structure of the...

Hello, I see that the development of the library has slowed down a bit, hence I would like to ask if there exists a roadmap for the first stable release...

Usage with glfw - imgui

8

Hi! Are there any examples about the usage with `glfw`? I'm trying to understand if I can use `fastplotlib` with https://github.com/pthom/imgui_bundle (that relies on `glfw`). Thanks a lot!

[Bug]: Allow extra kwargs in to_onnx() and/or engine.export() to be passed to torch.onnx.export

2

### Describe the bug When trying to export a model larger than 2GB, onnx throws the following error: ```bash RuntimeError: The serialized model is larger than the 2GiB limit imposed...

🐞 Padim - Difference in Engine prediction vs ONNX or Torch prediction

7

### Describe the bug Hi, I am sorry to bother you, but I can't get an exported ONNX model to work at inference time as inside the `engine.predict()` method. In...

[Discussion] Distribute multiple models across different MLServer instances

1

Hi! I would like to open a discussion to gather some advices, in case anyone has had similar experiences or has better ideas than mine. I am currently facing a...

### Description It would be nice being able to use custom lag transformations that do not rely on numba. For example, I was exploring the usage of the [catch 22](https://github.com/DynamicsAndNeuralSystems/pycatch22)...