Name and Version
Docker Image: beellama.cpp:server-cuda-preview-v0.3.2
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-server
Command line
--models-preset /llama-server/settings.ini --slot-save-path /llama-server/kv-cache
Problem description & steps to reproduce
Try using an mp4 or webm with a multimodal model. Images work fine.
In the webui "Failed to load image or audio file"
I was able to restore functionality by copying a staticaly built version of ffprobe and ffmepg to /usr/local/bin
First Bad Commit
No response
Relevant log output
E probe: failed to launch ffprobe
E mtmd_helper_video_init_from_buf: ffprobe failed on buffer (is ffprobe in PATH?)
E mtmd_helper_bitmap_init_from_buf: failed to decode buffer as either image/audio/video
Name and Version
Docker Image: beellama.cpp:server-cuda-preview-v0.3.2
Operating systems
Linux
Which llama.cpp modules do you know to be affected?
llama-server
Command line
Problem description & steps to reproduce
Try using an mp4 or webm with a multimodal model. Images work fine.
In the webui "Failed to load image or audio file"
I was able to restore functionality by copying a staticaly built version of ffprobe and ffmepg to /usr/local/bin
First Bad Commit
No response
Relevant log output
E probe: failed to launch ffprobe
E mtmd_helper_video_init_from_buf: ffprobe failed on buffer (is ffprobe in PATH?)
E mtmd_helper_bitmap_init_from_buf: failed to decode buffer as either image/audio/video