alt Hacker Newscurious that they are doing speculative decoding and not baking MTP into the model, like Nemotron
https://docs.nvidia.com/megatron-core/developer-guide/0.15.0...
curious that they are doing speculative decoding and not baking MTP into the model, like Nemotron
https://docs.nvidia.com/megatron-core/developer-guide/0.15.0...
They're using the term speculative decoding but doing MTP. It's the same thing as Nemotron, but Google removed the MTP heads from the original safetensora release. (They were not removed from the LiteRM format.)