Ming-Hsuan-Tu

large number of bounding boxes

8

Since the maximum number of cuda threads is 1024. So if the number of bounding boxes exceeds 1024 (count > 1024), the current implementation won't work. https://github.com/jeetkanjani7/Parallel_NMS/blob/master/GPU/nms.cu#L104 Any idea?

Any plan for dinov2?

2

DinoV2 has shown remarkable performance on downstream tasks, but its use of Vision Transformer (ViT) is computationally inefficient. Do you have plans to train an efficientVIT version of DinoV2?

Failed to load vit_large_patch14_clip_336.openai

1

converter ```python python convert-pth-to-ggml.py --model_name vit_large_patch14_clip_336.openai --ftype 1 ``` runner ```python ./bin/vit -t 4 -m ../ggml-model-f16.gguf -i ../assets/tench.jpg ```  Any idea?

is it possible to use cuda

4

Hi, is it possible to use cuda for inference?

 sometimes it does not have response and sometimes no text-to-speech generated. why?

which browser you used?

1

I am exprementing issues when using firefox and chromium. for firefox it would throw the exception in main.js ``` Connecting AudioNodes from AudioContexts with different sample-rate is currently not supported....

exec /__e/node20/bin/node: no such file or directory

3

```yml on: pull_request: types: [opened, synchronize] name: Tag Created jobs: tag-created: runs-on: rtx4090-1 container: image: nvcr.io/nvidia/l4t-tensorrt:r8.0.1-runtime steps: - name: Checkout code uses: actions/checkout@v4 with: ref: v0.2.0 ... ``` I am...