[GH-ISSUE #660] Feature Request / 功能需求: 增加并发支持 #483

Closed
opened 2026-10-29 14:40:20 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @yeungtuzi on GitHub (Feb 25, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/660

在系统能够支持20+ tps的情况下(假定),提供多线程并发服务能力,这样可以共享内存和显存数据,避免多进程多开的额外内存和显存浪费。
When system is powerful enough, provide --parallels parameter to provide more usable service.

Originally created by @yeungtuzi on GitHub (Feb 25, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/660 在系统能够支持20+ tps的情况下(假定),提供多线程并发服务能力,这样可以共享内存和显存数据,避免多进程多开的额外内存和显存浪费。 When system is powerful enough, provide --parallels parameter to provide more usable service.
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
kvcache-ai/ktransformers#483
No description provided.