热点
"oLLm" 相关文章
Meet oLLM: A Lightweight Python Library that brings 100K-Context LLM Inference to 8 GB Consumer GPUs via SSD Offload—No Quantization Required
MarkTechPost@AI 2025-09-29T17:47:04.000000Z
8GB显卡的逆袭！SSD换显存，3060 Ti硬跑100k长上下文
PaperWeekly 2025-09-28T16:13:02.000000Z
8GB显卡的逆袭！SSD换显存，3060 Ti硬跑100k长上下文
PaperWeekly 2025-09-28T16:06:41.000000Z