类库 › dflash-mlx
Aryagm

Aryagm/dflash-mlx

基于MLX框架为Apple Silicon设备实现DFlash推测解码加速库,可显著提升大语言模型(如Qwen3/3.5)的推理速度,支持命令行和Python API调用。

Aryagm/dflash-mlx

截图

Benchmarks

评论

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.1. UTC+08:00, 2026-04-20 22:46
浙ICP备14020137号-1 $Map of visitor$