mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-11-05 01:07:28 +00:00
[GH-ISSUE #181] 如何提升推理速度? #102
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/ktransformers#102
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @zerotorunaway on GitHub (Feb 13, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/181
根据FAQ中提示,越多核心可以达到越好效果。请问有没有这方面的实践,如四路、八路u。推理速度和多少路呈什么关系
@lulu2048 commented on GitHub (Feb 13, 2025):
单路512G和双路512G性能区别不大,四路和八路推理性能下降,主要受CPU间互联带宽限制。听说cpu_infer 20附近推理速度最佳最佳,启用核心太多会互相争抢内存带宽,可以用二分法测试
@yansiyu550 commented on GitHub (Feb 18, 2025):
是用CPU推理吗?不需要看CPU和GPU之间的带宽吗?
@ErvinXie commented on GitHub (Dec 11, 2025):
This issue has been automatically closed due to inactivity for 60 days.
If you believe this issue is still relevant, please feel free to reopen it with additional information or context.
Thank you for your contribution to KTransformers!
此 issue 因超过 60 天无活动而被自动关闭。
如果您认为此问题仍然存在,请随时重新打开并提供更多信息或上下文。
感谢您对 KTransformers 的贡献!