Diego Fiori

Hi @Ierezell, and thank you so much for your comment!We currently support the ONNX format, but just in the background! To be more specific, the PyTorch and TensorFlow models are...

Hi @NicoJuicy. We are not currently supporting TF Lite, but this can definitely be an interesting feature to include in the future! In the coming days we will draw up...

Hi @mali19064! Thank you for reaching out! Regarding your problem, I think it is due to the fact that nebullvm optimizes the model by considering the largest possible input size....

> same here, for https://github.com/nebuly-ai/nebullvm/blob/main/resources/notebooks/Accelerate-PyTorch-YOLO-with-nebullvm.ipynb as well, I am not getting any improvements, rather the same/or more latency. Hello @ukdsvl, could you please share with us your hardware configuration and...

Thanks ogencoglu. We are working right these days on building use cases to show both how to use the library in a more granular way and to provide benchmarks on...

@kartikeyporwal 🥇🚀 thanks for the amazing contribution ⭐! However, there are a few things to change before merging the code to master (See specific comments in the code section). BTW,...

Hi jues!!! You raised a good point that is indeed missing in the documentation! You can load the model by running the following commands ``` from nebullvm.inference_learners.base import LearnerMetadata path...

Hi @ehartford, thank you for reaching out. Support for PEFT is clearly one of our short-term goals. In addition, we are working to improve integration with DeepSpeed and support weight...

Hello @BrianPulfer! Thank you very much! I assigned the issue to you. Feel free to ping me if you have any question about the issue or the code.

Hello @Yash-coder916, thanks for sharing the error. It seems that the problem is related to some missing inputs to the HF model. The T5 architecture is an encoder-decoder architecture, so...