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
12 lines
342 B
Python
12 lines
342 B
Python
"""
|
|
ComfyUI-PromptTranslator-Enhancer
|
|
Translates and enhances prompts from multiple languages to English using local GGUF models.
|
|
"""
|
|
|
|
from .nodes import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
|
|
|
|
__version__ = "1.0.0"
|
|
__author__ = "EzeTojo"
|
|
|
|
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS", "__version__", "__author__"]
|