pvtoan

Hi, I got exactly the same problem as @sudamerushabh . Appreciate any help!

Hi @ryanshrott, 1. If you are using VLLM via LangChain, so, the correct code is as follows. from langchain.llms import VLLM model = VLLM(model=model_path, tensor_parallel_size=1, trust_remote_code=True, vllm_kwargs={"quantization": "awq"}) 2. Other...

Hi @Fenkail , I already modified the "ray_utils.py" as you suggested but the problem is still there. In fact, my pc has only two GPUs. So, I'd like to know...

Yes, I did modify ray_utils.py, installed in my conda environment for vllm

Hi @vietanhdev, I used Segment Anything (ViT-L) but it also loaded to RAM (not GPU). Can you please check what the problem is? Thank you!

Hi, I saw that the two files including build.sh and setup.py are not properly written for Windows. These files are only used for Linux because output files are *.so (for...

Hi, Thank you so much for sharing your interesting work! At present, I am trying to understand about online_demo code. In particular, the variable "window_frames" will be appended continuously as...

Hi @nikitakaraevv, Thank you for your clear answer. Btw, when I already "discarded" previous frames of variable "window_frames" (it means the input of function "CoTrackerOnlinePredictor" has a fixed size) However,...

Hi @nikitakaraevv , I tried to update with the two commands in "cotracker.py", as you showed self.online_coords_predicted = coords_predicted[:, ind : ind + S] self.online_vis_predicted = vis_predicted[:, ind : ind...

Hi @nikitakaraevv , If you have time, please take a look at my issue. Thank you for your help!