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).
跟着老特的视频找过来了,我windows下,跑楼主的参数,只有7t/s,看是内存用到共享内存到了1.2g,自然就慢了。调小了上下文长度到96k,并行2,hermes正常解决几个问题就oom了。速度也是能在50t/s的样子。现在调成了80k,并行2,再看看情况吧。