RoyaltyLJW comments

Results 13 comments of


                                            RoyaltyLJW

Memory leak if stream is not explicitly closed

hi, @meakbiyik Have you found any solution to deal with the problem? I find that if i break before all the frame extracted, stream.close causes everything to hang

Memory leak if stream is not explicitly closed

@meakbiyik Thanks a lot. It fix my deadlock issue

core dumped in frame extract

What's more, memory leak happen in the code below due to opencv operation ```python def generator_mode(input_list): input_path,threads = input_list start = time.time() graph = bmf.graph() video = graph.decode({ 'input_path': input_path,...

CPU Video Frame Extraction

Thanks, I will try it. Is it can run in cpu?

CPU Video Frame Extraction

It seems that it use encode module to save the frame in JPEG format, but i do not want to save it as a file. Instead, I want to get...

CPU Video Frame Extraction

Thanks a lot, the ffmpeg version I test with two ways is the same. I will try it later

Parallel inference is wrong but single card inference is correct. (can't be solved by updating nvidia driver like #331)

> Hello! This error may be caused by the I/O virtualization of the device, which blocks the P2P communication between the cards, I solve it by disabling the I/O virtualization...

[Bug]: vllm infer Qwen2.5-32B-Instruct-AWQ with 2 * Nvidia-L20, output repeat !!!!

Yes, and I tried some of the methods mentioned in these two issues, but it doesn't work. Set the system prompt length more than 50 is also useless

[Bug]: vllm infer Qwen2.5-32B-Instruct-AWQ with 2 * Nvidia-L20, output repeat !!!!

@kratorado @Tejaswgupta What type of GPU do you use for inference? nvidia-A series （A30） or nvidia-L series (L20) I tried to infer on A30, but failed to reproduce. As mentioned...