Ssignal
17
·7天前·1 signals
Archived topic · 归档话题，来源已停止追踪
3 days benchmarking most llama.cpp flags on my weird 40gb vram laptop + tb4 egpu setup. Got +70% generation, +40% prefill, 60k more context, and filed a bug in llama around MTP. What I learned.
LlamaNVIDIA端侧推理
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。