Ezequiel Tojo
0ca8dd2ce6
Major improvements: - Automatic GPU to CPU fallback with VRAM management - Free PyTorch CUDA cache before each load attempt - CPU-pure mode: op_offload=False, flash_attn=disabled, offload_kqv=False (prevents llama.cpp from allocating ~606 MiB CUDA compute buffers) - Progressive context reduction (4096 -> 2048 -> 512) - Vision-Language model detection and filtering (Qwen3VL, LLaVA, etc.) - Proactive CUDA DLL registration for Windows - Always-verbose mode for native llama.cpp diagnostics
26 lines
183 B
Plaintext
26 lines
183 B
Plaintext
# Python
|
|
__pycache__/
|
|
*.py[cod]
|
|
*$py.class
|
|
*.so
|
|
*.whl
|
|
|
|
# ComfyUI
|
|
models/
|
|
output/
|
|
input/
|
|
|
|
# IDE/Editor
|
|
.vscode/
|
|
.idea/
|
|
*.swp
|
|
*.swo
|
|
|
|
# OS
|
|
.DS_Store
|
|
Thumbs.db
|
|
|
|
# Misc
|
|
.tracking
|
|
.gemini/
|