Replies: 1 comment
|
Yes, the latest rolling release should support it. https://github.com/LostRuins/koboldcpp/releases/tag/rolling give it a try with dspark draft model |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
The DeepSeek V4 Flash model works great for me but I would like to speed up inference with DSpark which I guess is their version of MTP - are there any plans to support this?
All reactions