Any hope for DeepSeek v3 MTP support?

[Green0-0]

"Based on our evaluation, the acceptance rate of the second token prediction ranges between 85% and 90% across various generation topics, demonstrating consistent reliability. This high acceptance rate enables DeepSeek-V3 to achieve a significantly improved decoding speed, delivering 1.8 times TPS (Tokens Per Second)."
(The DeepSeek v3 report)

[BarfingLemurs]

It may also be worth looking at DeepseekVL2 models which share the same vocabulary as DeepseekV3.

This one, maybe then it could be offloaded to the gpu?