MTP support merged into llama.cpp
Summary
The pull request adding MTP (Multi-Token Prediction) support to llama.cpp has been merged into the master branch.
Similar Articles
llama + spec: MTP Support by am17an · Pull Request #22673 · ggml-org/llama.cpp
Pull request adding Multi-Token Prediction (MTP) support to llama.cpp, enabling speculative decoding for faster inference.
llama.cpp adaptive MTP PR#27210
A pull request (PR#27210) for adaptive MTP has been submitted to llama.cpp, a C/C++ implementation for LLM inference with minimal setup and high performance.
you can now use MTP in GLM-Air
llama.cpp now supports MTP (Multi-Token Prediction) for GLM-Air models, enhancing inference capabilities for large language models in C/C++.
b9180 llama.ccp MTP landed
llama.cpp version b9180 has been released, featuring Multi-Token Prediction (MTP). The release is marked by successful builds and developer relief.
That's a good news...
Multi-token prediction (MTP) has been approved for integration into llama.cpp, indicating an upcoming update to the local LLM inference tool.