[GH-ISSUE #1710] 能否将kt微调deepseek-v3得到的lora权重与原始模型权重合并 #1092

Closed
opened 2026-10-29 14:48:23 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @SamsFirth on GitHub (Dec 12, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1710

Originally assigned to: @JimmyPeilinLi on GitHub.

Reminder

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

Description

能否将kt微调deepseek-v3得到的lora权重与原始模型权重合并,再在ke-kernel上通过sglang部署吗?sglang需要静态的模型权重,但是常规merge不可用。

虽然官方使用kt进行推理的方式不需要合并权重,但是我想通过sglang部署,因此merge功能貌似是必须的。

Pull Request

没有

Originally created by @SamsFirth on GitHub (Dec 12, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1710 Originally assigned to: @JimmyPeilinLi on GitHub. ### Reminder - [x] I have read the above rules and searched the existing issues. ### Description 能否将kt微调deepseek-v3得到的lora权重与原始模型权重合并,再在ke-kernel上通过sglang部署吗?sglang需要静态的模型权重,但是常规merge不可用。 虽然官方使用kt进行推理的方式不需要合并权重,但是我想通过sglang部署,因此merge功能貌似是必须的。 ### Pull Request 没有
bsakaguchi 2026-10-29 14:48:23 +00:00
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#1092
No description provided.