3.0.0-beta.46 (2024-09-20)

Bug Fixes

• no thread limit when using a GPU (#322) (2204e7a)
• improve defineChatSessionFunction types and docs (#322) (2204e7a)
• format numbers printed in the CLI (#322) (2204e7a)
• revert electron-builder version used in Electron template (#323) (6c644ff)

Shipped with llama.cpp release b3787

To use the latest llama.cpp release available, run npx -n node-llama-cpp source download --release latest. (learn more)