fix: `semantic-release` retry (#518) 

fix(Vulkan): include integrated GPU memory (#516) * fix(Vulkan): include integrated GPU memory - adapt to a change in `llama.cpp` * fix(Vulkan): deduplicate the same device coming from different drivers * fix: adapt Llama chat wrappers to breaking `llama.cpp` changes * fix: internal log level * docs(Vulkan): recommend installing LLVM on Windows

test: fix tests (#509) 

feat: Seed OSS support (#502) 

test: fix tests (#499) 

fix: split prebuilt CUDA binaries into 2 npm modules (#495) 

fix: CUDA 13 support (#494) fix: prebuilt binaries CUDA 13 support

fix: completion config (#490) * fix: more flexible model message prompt completion config * feat(Electron template): improve scroll

feat: `gpt-oss` support (#487) * feat: `gpt-oss` support * fix: Qwen3 memory estimation

build: fix CI config (#483) * build: update CUDA version in the CI * fix: add missing GGUF types