请教一下大家,glm0.3b有什么可用的推理加速的方法吗?目前我的推理任务要3秒钟一个,耗时太长
mechigonft opened this issue · comments
mechigonft commented
runningabcd commented
No description provided.
批量处理下
GLM (General Language Model)
mechigonft opened this issue · comments
No description provided.
批量处理下