#cplusplus
ik_llama.cpp is an improved version of llama.cpp that runs faster on CPUs and hybrid GPU/CPU setups. It supports many new advanced quantization methods, which help models use less memory and run more efficiently. It also offers better performance for special models like DeepSeek and MoE, with faster prompt processing and token generation. You can run it on various hardware, including Android, and it has features to control where model data is stored (CPU or GPU). This means you get quicker AI responses and can handle bigger or more complex models smoothly on your computer or device[2][1][4].
https://github.com/ikawrakow/ik_llama.cpp
Пока весь мир ждет доступа к новой модели со зрением GPT-4V(ision), опенсорс команда (пара азитов со степенью PhD из американских вузов) уже выпустили свой аналог и бесплатную версию #LLaVA (Large Language and Vision Assistant), которая выдает результат (не) хуже GPT4V и может работать локально.
Вот такая скорость развития и конкуренции в этом новом #AI рынке.
🧠LLava - вебсайт
📄WhitePaper
🧬Github code
🔋Demo для потестить на своих дикпиках
🦒Colab (для запуска у себя на серваке)
#python#apple_silicon#florence2#idefics#llava#llm#local_ai#mlx#molmo#paligemma#pixtral#vision_framework#vision_language_model#vision_transformer
MLX-VLM lets you run, chat with, and fine-tune Vision Language Models (VLMs) plus audio/video models on your Mac using MLX—install easily with `pip install -U mlx-vlm`. Use CLI for quick text/image/audio generation (e.g., `mlx_vlm.generate --model ... --image photo.jpg`), Gradio UI for chats, Python scripts, or a FastAPI server with OpenAI-compatible endpoints supporting multi-images/videos. Features like TurboQuant cut KV cache memory by 76%, and LoRA/QLoRA fine-tuning works on consumer hardware. You benefit by experimenting with powerful multimodal AI locally—fast, memory-efficient, no cloud costs, perfect for Mac users tweaking models affordably.
https://github.com/Blaizzy/mlx-vlm