gpu-inference
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
Mixed-vendor GPU inference cluster manager with speculative decoding
کتابخانه Moxra (مکسرا) برای تشخیص محتوای NSFW در پایتون با استفاده از ONNX، با پشتیبانی از تصاویر، GIF و ویدئو، پردازش CPU/GPU و پردازش ناهمگام.
GPU-accelerated LLaMA inference wrapper for legacy Vulkan-capable systems a Pythonic way to run AI with knowledge (Ilm) on fire (Vulkan).
Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind one endpoint.
