whats happening on llama.cpp
Summary
A significant update to llama.cpp requires all previously generated GGUF files to be regenerated, indicating a major breaking change to the model format.
Similar Articles
llama : website + unified `llama` binary · ggml-org/llama.cpp · Discussion #23875
Llama.cpp announces a new website and unified 'llama' binary for simpler LLM inference, along with updates like Hugging Face cache migration and multimodal support.
Release b11003 · ggml-org/llama.cpp
llama.cpp releases version b11003, a C/C++ tool for efficient large language model inference with minimal setup on a wide range of hardware.
Unsloth's Gemma 4 mmproj silently broke vision & audio on newer llama.cpp builds — anyone else hit this?
A developer reports that Gemma 4 multimodal features broke in newer llama.cpp builds when using Unsloth's GGUF models, due to an incompatible mmproj file. Switching to ggml-org's official models fixed the issue, highlighting a recurring compatibility concern between third-party quantizers and llama.cpp updates.
What's in a GGUF, besides the weights – and what's still missing?
This article explores the GGUF file format used by llama.cpp for language models, highlighting its single-file convenience and the role of embedded chat templates and special tokens. It also compares different Jinja implementations and discusses what is still missing from the format.
Llama.cpp version 0.2.0 is out!
Llama.cpp, a popular open-source tool for running LLaMA models, has released version 0.2.0 with changelog and pre-built binaries available on GitHub.