winstona
winstona
> Other ways around this problem are: > * using a quadro card > * https://github.com/keylase/nvidia-patch I missed mentioning allowing only 2 encoders on consumer cards specifically - the goal...
moving to draft as I have pending changes and identified a memory leak resulting from leftover nvenc resources
I've been working on this off and on, and have been trying to validate and ensure any potential long term memory leaks are addressed fully (some of these were a...
sorry about the delay and updating this one. I've had to step away from this for a bit, but I've been using this daily and working out the last bits...
rebased off of latest master - it appears to be functional at this point, however I have a few comments to fix/address before considering this ready to merge
adding a similar but slightly different use case/scenario for a CPU fallback option: I have frigate running in a kubernetes cluster - usually on a node with a GPU. If...
I recently switched over from CPU -> GPU detection and have run into this issue multiple times recently when the node fails, leaving it in a restart loop for hours...
sorry for not making it more clear, @clearwave1 - it is implemented with a few changes in the frigate code, PR here: #10440 , however it looks like based on...