[GH-ISSUE #955] OpenAI API后台上下文长度支持 #680

Closed
opened 2026-10-29 14:42:48 +00:00 by bsakaguchi · 1 comment
Owner

Originally created by @1556900941lizerui on GitHub (Mar 21, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/955

我想请问一下在使用API调用服务时支持的上下文长度是否最高也为139K,我看到相关咨询说API模式下只支持1K上下文,这是否有误?

Originally created by @1556900941lizerui on GitHub (Mar 21, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/955 我想请问一下在使用API调用服务时支持的上下文长度是否最高也为139K,我看到相关咨询说API模式下只支持1K上下文,这是否有误?
Author
Owner

@Atream commented on GitHub (Mar 22, 2025):

https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/DeepseekR1_V3_tutorial.md#v022--v023-longer-context--fp8-kernel
参照这个链接进行修改即可,server端也可以使用

<!-- gh-comment-id:2744971517 --> @Atream commented on GitHub (Mar 22, 2025): https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/DeepseekR1_V3_tutorial.md#v022--v023-longer-context--fp8-kernel 参照这个链接进行修改即可,server端也可以使用
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#680
No description provided.