Hugging Face Blog·· 2 d ago
llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem
llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem
AI summary
llama.cpp makes it possible to run multi-modal LLMs across a wide range of hardware - from consumer-grade local machines to high-end enterprise servers. Today we release libraries v1.0.0, highlighting our responsibility to those developers.
Selection record
Threshold 60Official, first-handFirst 62Second 58
AdmittedSum of both 120 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：llama.cpp本地AI推理框架发布
- Why it was chosen
- Sets out the versioning rules llama.cpp and ggml follow from v1.0.0, so downstream integrations can tell how API and ABI changes will be signalled.
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Hugging Face Blog · huggingface.co