v4.4.2
📦 localaiView on GitHub →
🐛 2 fixes🔧 2 symbols
Summary
This patch updates underlying dependencies including llama.cpp and CrispASR, and resolves critical bugs related to vLLM tool argument parsing and CUDA environment setup.
🐛 Bug Fixes
- Fixed an issue in vLLM where tool_call function arguments were parsed after applying the chat template.
- Fixed an issue in CUDA builds by ensuring cuda-nvrtc-dev is installed alongside other CUDA development packages.