← Tuesday, October 6, 2026InferenceRelease

llama.cpp adds MTP decoding and new attention kernels in v0.6.0

github.com 19 min read Editor score 8/10

The release adds MTP speculative decoding for Qwen4Exp, with a reported ~1.5× decode speedup on DGX Spark, plus Metal flash attention and sparse Vulkan attention. These changes offer concrete options for improving local inference performance.

What

llama.cpp v0.6.0 adds extended batching, new model support, speculative decoding, and attention kernels.

How

The llama_batch_ext API handles mixed token and embedding batches; the release also adds MTP decoding and Metal and Vulkan attention improvements.

Why it matters

Inference engineers gain support for more model types and input modes, plus kernel and speculative-decoding changes aimed at faster execution.

Read on github.com →

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.