fatih akyon comments

Results 220 comments of


                                            fatih akyon

fix: specify a device other than cuda:0

@0xf21 perfect addition, thanks!

[New Model]: Florence-2

Both https://github.com/vllm-project/vllm/pull/5852 and https://github.com/vllm-project/vllm/pull/5276 is merged. Do you still have plans to work on this PR @chandeldivyam ?

[New Model]: Florence-2

@chandeldivyam Yes, I also need such a solution for my work. I'm trying to utilize https://github.com/Lightning-AI/LitServe since I only have a little experience with the vllm-project.

Feature: Add Support for Azure OpenAI Embeddings

We also need Azure OpenAI support in LanceDB embedding functions. Is there any update on this feature? @AyushExel @QianZhu

Feature Request: Gradio library support

You can write in this issue at Gradio: https://github.com/gradio-app/gradio/issues/1382

attempt_download_from_hub, using newly uploaded https://huggingface.co/Ultralytics/YOLOv5/tree/main

@topherbuckley ill look into it once i found the time 🚀

empty segmentation fix

Closing this due to inactivity, it might already be fixed in the latest version of SAHI.

Embeddings

Thanks for the great project @MahmoudAshraf97 I am up to achieve the same as @Brihith ! Could you direct us to some documents or give us hints on this @MahmoudAshraf97

I modified a part of the code to enable parallel inference with multiple num_batch

Great @zhugelaozei ! Can you please fix the formatting by: 1. Install development dependencies: pip install -e ."[dev]" 2. Run code formatting: python -m scripts.run_code_style format

fix(sahi): Fix Polygon Repair and Empty Polygon Issues

@SunHao-AI can you please [fix the failing tests ](https://github.com/obss/sahi/actions/runs/13666381802/job/38208423661?pr=1118)🤗