XTC Sampling Is Already Built Into llama.cpp and Other Open-Source Inference Engines

ziv_ravid · x · 2026-09-26

The author notes that XTC sampling is already built into llama.cpp, ExLlamaV2, text-generation-webui and other open-source inference engines, so anyone running models locally can likely use it today.

The accompanying paper finally provides a proper formalization and evaluation of the technique that the open-source community has been using in practice.

Related event: XTC sampling lands in llama.cpp and other open-source engines(2 posts)→

Original post →

More from Infra

Infra channel →