Divided by Zer0
Divided by Zer0
This is a brand new payload feature, which prevents a shared key from stopping when it or its user runs out of kudos. Instead it downgrades the resulting request priority...
- For recurring parties, allow to specify max amount of rewards per person (so someone doesn't just abuse the feature) - Allow the creator to optionally specify a "winner" somehow....
Purging a user doesn't purge their communities. Might be good to give a method for admins who want to do that. The method should look up all user-owned communities and...
You are already checking for endorsements for each instance, so you can also grab the self-assigned tags if any exist and show them as well. Optionally make each tag a...
The [AI Horde](https://aihorde.net) is a crowdsourced generative AI cluster for people to share compute. This can allow everyone to use this tool, and not only those with powerful GPUs. The...
It was [brought to my attention](https://discord.com/channels/781145214752129095/1042786389474947112/1201194773625712660) that currently we do not appear to be compressing the images a lot when R2 is disabled. This introduces significant bandwidth through b64 transfers...
From the logs of cozmyc, I noticed some weird OOM errors about Post-processors even though there should be more than enough VRAM. I don't quite understand why since I thought...
When an exception occurs in `horde_worker_regen.process_management.worker_entry_points:start_inference_process` the worker ends up in a stuck state where it's endlessly rotating models between its queues. Also see: * https://github.com/Haidra-Org/hordelib/issues/152 * https://github.com/Haidra-Org/horde-model-reference/issues/72
Hey everyone. I'm thinking of moving this framework to an MIT license. With my other work on my FOSS, I haven't had much time to maintain it anymore and move...
https://github.com/Alpha-VLLM/Lumina-T2X