Ssignal

17

08/08 18:00·2天前·1 signals

Archived topic · 归档话题，来源已停止追踪

PSA for anyone with multiple V620's or other gfx1030 cards having problems making llama.cpp tensor split work -- set "-ub 384" and -b to a multiple of that depending on number of GPUs

Llama

热度趋势

趋势数据积累中

百分比基于当前可用热度信号，而非评论数或独立用户人数。