turboderp/exllama
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
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
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.