quinn50
quinn50
Seeing this issue aswell with dual intel arc b50 pros, also happens with just one GPU installed. Most models work with fresh chats in open webui but larger character files...
oobabooga has a openai compliant API now so you could run this privately assuming you have the hardware. https://github.com/oobabooga/text-generation-webui/wiki/12-%E2%80%90-OpenAI-API
Same issue here with dual intel arc b50 pros, some models work some models throw this error intermittently
Hi, I got ahold of a intel b50 pro and also seeing similar issue with intermittent runs for 7b and under models. Card should be able to load q4 24b...