v3.14.1
3.14.1 (2025-10-26)
Bug Fixes
- Vulkan: include integrated GPU memory (#516) (47475ac)
- Vulkan: deduplicate the same device coming from different drivers (#516) (47475ac)
- adapt Llama chat wrappers to breaking
llama.cppchanges (#516) (47475ac)
Shipped with llama.cpp release b6843
To use the latest
llama.cpprelease available, runnpx -n node-llama-cpp source download --release latest. (learn more)