Newshot Local inference engine llama.cpp 1.0.0 epic update: supports over 150 model architectures, runs large models at full capacity even offline
IT Home, November 14 news — developer Georgi Gerganov (X account @ggerganov) posted on X yesterday (November 13), announcing that the open-source AI inference project llama.cpp and the library version of the underlying machine learning engine ggml have entered 1.0.0.
According to public information reviewed by IT Home, Gerganov is the creator of the open-source project llama.cpp and an important developer of local AI foundational software such as ggml and whisper.cpp. In his personal X bio he identifies himself as a Hugging Face engineer, with his GitHub location listed as Sofia, Bulgaria.
llama.cpp is an open-source AI inference project written primarily in C/C++, whose core purpose is to let large language models run on various hardware such as personal computers and servers. It can be used both for local deployment and for cloud services, with the goal of reducing deployment complexity and fully utilizing a device's computing power.
The biggest highlight of this update is the explicit interface compatibility rules:
| Item | Library | Role |
|---|---|---|
| llama.cpp | libllama | C/C++ large model inference library |
| ggml | libggml | Underlying machine learning tensor library |
Going forward, both will mark API or ABI-incompatible changes clearly through major version number upgrades, so that applications depending on these libraries can identify upgrade boundaries. For developers, it becomes easier to judge from the version number whether a given upgrade may require corresponding changes to their own applications. The official version rules are:
| Version digit | When it is updated |
|---|---|
| MAJOR, e.g. 1.x.x → 2.0.0 | Breaking changes to the public C API in ./include; the announcement also clarifies that API / ABI incompatibilities will be reflected through major version upgrades |
| MINOR, e.g. 1.0.x → 1.1.0 | Backward-compatible features, backend updates, model support, or API additions |
| PATCH, e.g. 1.0.0 → 1.0.1 | Bug fixes that do not change the API |
On engineering quality, the official announcement said that to support the continuously accelerating development pace, the team emphasized three commitments:
- Using Hugging Face's HF Buckets and HF Jobs to scale CI infrastructure.
- With hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM, and Intel, continuously adding self-hosted test runners covering major hardware platforms.
- Judiciously using LLMs in the development process, while continuing to prioritize code quality, architectural control, and understanding of implementation details.
On backend and model support, ggml supports different hardware through dedicated backends; each backend can be compiled as a dynamic library and loaded at runtime as needed.
llama.cpp already supports over 150 model architecture variants and mainstream speculative decoding methods. The team will also continue to strengthen automated testing infrastructure and, with hardware support provided by 英伟达, AMD, Qualcomm, Arm, IBM, and Intel, expand cross-platform test coverage.
Related articles
- Meta to take Llama API public preview offline tomorrow
- Meta: Uploading pirated books via BitTorrent constitutes fair use
- Built on the Llama model: Meta to bring AI-driven NPCs to its VR metaverse platform Horizon World
- Report: Meta splits AI division into two teams, focusing on consumer products and foundational AGI research respectively
- Meta launches incentive program to help startups adopt its Llama AI models, subsidizing up to $6,000 per month
- Meta Llama AI model downloads surpass 1.2 billion, with developers contributing tens of thousands of derivative models