Daniel Huang

Any idea on if this will be implemented in core? The PR (#4545) for this issue hasn't had any progress since November 2022.

I'm having this issue as well, it seems to work again if you disable then enable again in the extension menu (not in the firefox preferences)

| Performance (s) | A100 | Gaudi2 | |--------|--------|--------| | BF16 | 0.02548 | 0.01313 | | FP32 | 0.05736| 0.01962 | Testing setup: - 100 sequential model passthroughs of...

I added the patch. I ran the script with multiple video inputs from [TempoFunk/webvid-10M](https://huggingface.co/datasets/TempoFunk/webvid-10M): ```sh python run_example.py -bg -w 3 \ --video_paths https://ak.picdn.net/shutterstock/videos/5629184/preview/stock-footage-senior-couple-looking-through-binoculars-on-sailboat-together-shot-on-red-epic-for-high-quality-k.mp4 \ https://ak.picdn.net/shutterstock/videos/21179416/preview/stock-footage-aerial-shot-winter-forest.mp4 \ https://ak.picdn.net/shutterstock/videos/1063125190/preview/stock-footage-a-beautiful-cookie-with-oranges-lies-on-a-green-tablecloth.mp4 \ https://ak.picdn.net/shutterstock/videos/1039695998/preview/stock-footage-japanese-highrise-office-skyscrapers-tokyo-square.mp4 \...

Made a PR which I think works for all the cases I can think of. Let me know if I missed anything!