Jeevithan Alagurajah
Jeevithan Alagurajah
I have same problem can anyone help?
GST_DEBUG=3 gst-launch-1.0 v4l2src device=/dev/video0 ! video/x-raw,width=1280,height=720,format=UYVY ! videoconvert ! autovideosink -v the above code actually works! however I couldn't get the stream through video-viewer, or VideoSource API? Can anyone help...
Any plan to support Lora weights directly without needing of merging?
I would also like to have this feature as well, this would be great feature to have
I tried all of this and still my volatile memory is zero. @lamsach, Can you please provide some details about how did you manage to get it run ?
@StephennFernandes Thank you for your reply. ## Resources for dynamic lora: https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/enc_dec#run-bart-with-lora https://github.com/cccntu/minLoRA/tree/main https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/llama#run-llama-with-several-lora-checkpoints https://github.com/S-LoRA/S-LoRA # I have provided some example repos where I got the idea from. Unfortunately I...
@StephennFernandes I am looking forward to it.
Whisper tiny.en/small.en/medium.en aren't transcribing well (quality is low) Whisper tiny/small/medium are doing good. Can someone please explain this ?
Can you please have lora support for whisper?
I am commenting here to remove stale