ms-swift icon indicating copy to clipboard operation
ms-swift copied to clipboard

Published 20 hours ago • verified publisher icon modelscope

72B的模型首字延时如何减少

Open HJT9328 opened this issue 10 months ago • 0 comments

部署了qwen1.5-72B的模型，测试流式首字延时大概在1.6s，通过什么参数能够减少首字延时呢，求大神

HJT9328 avatar Apr 12 '24 02:04 HJT9328