Artificial Analysis· @ArtificialAnlys · X·· 3 小时前AI 评分31
AI 导读
我们还在测试更多权重格式和运行时，包括更小的 4-bit 格式如 IQ4_XS，以及 Inco AI 的 Splash——一个面向 Apple Silicon 的 Metal 引擎，使用 DFlash 投机解码。等它们通过我们的准确性检查后，我们会加入其结果，检查结果也将很快发布。早期测试显示在某些系统上完成时间更快
正文
We are also testing more weight formats and runtimes, including smaller 4-bit formats such as IQ4_XS and Inco AI's Splash, a Metal engine for Apple Silicon that uses DFlash speculative decoding. We will add their results once they pass our accuracy checks, which we will publish soon. Early tests show faster completion times on some systems
来源：Artificial Analysis · x.com