johnfink8/sfnx
CUDA engine that splits every layer of a production quality MoE LLM across three PCIe V100 cards delivering 382 tok/s on a used $1,800 box.
正在读取项目信息…
开源雷达国内 GitHub 镜像站
加速通道已就绪
返回列表
开源雷达国内 GitHub 镜像站
CUDA engine that splits every layer of a production quality MoE LLM across three PCIe V100 cards delivering 382 tok/s on a used $1,800 box.