公开(公告)号：US20240028392A1

公开(公告)日：2024-01-25

申请号：US18323086

申请日：2023-05-24

申请人： ALIBABA (CHINA) CO., LTD.

发明人： XUECHAO WEI ,  ZHE ZHOU ,  JIEJING ZHANG ,  SICHENG LI ,  YEN-KUANG CHEN ,  BIZHAO SHI

IPC分类号： G06F9/48

CPC分类号： G06F9/4881 ,  G06N5/04

摘要： The present disclosure discloses a batch computing system and an associated method. The batch computing system includes a memory, a task manager and an inference computer. The memory stores a shared model parameter set common to a plurality of tasks that is generated by fine tuning a shared model and a task-specific parameter set of each task. The inference computer receives a plurality of task requests, derives a data length and a designated task of each task request, and enables the task manager to read a task-specific parameter set and a shared model parameter set corresponding to each task request. The inference computer further assigns task requests corresponding to the shared model to a plurality of computation batches, performs, in batch, the common computation of designated tasks in each batch computation, and performs task-specific computation operations of the designated tasks of each batch computation.