Daniel Han 2b7a787075 studio: cross-platform llama.cpp builder (Linux, macOS, Windows) ... - Linux: CUDA detection via /usr/local/cuda*, Ninja preferred - macOS: Metal backend auto-enabled (llama.cpp default), no CUDA - Windows: CUDA via CUDA_PATH env and toolkit dirs, VS generator fallback, binaries in build/bin/Release/, copy instead of symlink - Reuse existing source (don't re-clone if CMakeLists.txt present) - Both llama-server and llama-quantize verified and built		2026-03-16 14:21:54 +00:00
..
__init__.py	Final cleanup	2026-03-12 18:28:04 +00:00
audio_codecs.py	studio: per-model inference defaults, GGUF slider fix, reasoning toggle (#4325)	2026-03-16 06:37:55 -07:00
defaults.py	chat only with gguf for mac devices (#4300)	2026-03-15 23:20:48 +04:00
inference.py	studio: per-model inference defaults, GGUF slider fix, reasoning toggle (#4325)	2026-03-16 06:37:55 -07:00
llama_cpp.py	studio: per-model inference defaults, GGUF slider fix, reasoning toggle (#4325)	2026-03-16 06:37:55 -07:00
llama_cpp_builder.py	studio: cross-platform llama.cpp builder (Linux, macOS, Windows)	2026-03-16 14:21:54 +00:00
orchestrator.py	[pre-commit.ci] auto fixes from pre-commit.com hooks	2026-03-16 02:46:56 -07:00
worker.py	Set repetition_penalty default to 1.0 (disabled) everywhere	2026-03-16 02:46:56 -07:00