Your browser does not seem to support JavaScript. As a result, your viewing experience will be diminished, and you have been placed in read-only mode.
Please download a browser that supports JavaScript, or enable it if it's disabled (i.e. NoScript).
你这个prefill速度不对劲，怎么只有1300tok/s，建议把--prefill 从 auto:6144 改成 auto:32768，32k以上输入情况下，prefill速度能提升到2600tok/s，32k以下输入也能保持2000tok/s。如果再把引擎升级到0.1.56(默认起草器从mtp变成了dflash2)，prefill可以进一步提升到3000tok/s。
V