[GH-ISSUE #1665] KTMoEWrapper使用 #1070

New issue

Open

opened 2026-10-29 14:48:11 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-29 14:48:11 +00:00

Owner

Originally created by @liangminghuang on GitHub (Dec 4, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1665

Originally assigned to: @ovowei on GitHub.

Reminder

I have read the above rules and searched the existing issues.

Description

0.4.2版本kt-kernel教程主要采用sglang推理的方式，如何使用python api的方式（KTMoEWrapper），没有详细的使用指南。

Pull Request

No response

Originally created by @liangminghuang on GitHub (Dec 4, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1665 Originally assigned to: @ovowei on GitHub. ### Reminder - [x] I have read the above rules and searched the existing issues. ### Description 0.4.2版本kt-kernel教程主要采用sglang推理的方式，如何使用python api的方式（KTMoEWrapper），没有详细的使用指南。 ### Pull Request _No response_

bsakaguchi added the

enhancement

label

2026-10-29 14:48:11 +00:00

bsakaguchi commented

2026-10-29 14:48:12 +00:00

Author

Owner

@ErvinXie commented on GitHub (Dec 8, 2025):

Please inspect how we use it in sglang, we currently do not have any detailed documents of them.

@ErvinXie commented on GitHub (Dec 8, 2025): Please inspect how we use it in sglang, we currently do not have any detailed documents of them.

bsakaguchi commented

2026-10-29 14:48:12 +00:00

Author

Owner

@ovowei commented on GitHub (Dec 16, 2025):

KTMoEWrapper is an operator wrapper that does not provide inference separately. The documentation describes direct python API usage.

@ovowei commented on GitHub (Dec 16, 2025): KTMoEWrapper is an operator wrapper that does not provide inference separately. [The documentation](https://github.com/kvcache-ai/ktransformers/blob/main/kt-kernel/README.md) describes direct python API usage.