~/LLM INFERENC/llama-cpp-b10228-released-with-support-for-deepseek-v4-mtp-and-dspark

llama.cpp b10228 Released with Support for DeepSeek-V4 MTP and DSpark

The b10228 release of llama.cpp introduces support for DeepSeek-V4's Multi-Token Prediction (MTP) and DSpark. This update integrates these features directly into the local LLM inference engine. This release enables local deployment of DeepSeek-V4 models with significantly accelerated inference speeds. By leveraging MTP and DSpark, users can run highly efficient speculative decoding without needing a separate draft model. The update is tracked under pull request #25784 and is available across multiple platforms, though KleidiAI support for macOS Apple Silicon remains disabled in this build.

## BACKGROUND

Multi-Token Prediction (MTP) is a speculative decoding method where a language model natively predicts multiple future tokens at once to speed up generation. DSpark is an inference optimization technology developed by DeepSeek that significantly accelerates model execution. llama.cpp is a popular open-source C/C++ library designed for running large language models locally with high efficiency.

## REFERENCES

## KEYWORDS

#LLM Inference#llama.cpp#DeepSeek-V4#AI/ML#Open Source

$ subscribe --daily

llama.cpp b10228 Released with Support for DeepSeek-V4 MTP and DSpark | Daily News