AI is happening. The future is updating.locate-anything.cpp-gguf
GGUF builds of `nvidia/LocateAnything-3B` for **locate-anything.cpp** - a C++/ggml inference engine for open-vocabulary detection / visual grounding, no Python at inference time. The detections are the same as the official PyTorch implementation (the engine is parity-gated against it), and it runs faster - on CPU and GPU. The full-precision `f32` GGUF (~15 GB) is reproducible from the HF weights with `scripts/convert_locateanything_to_gguf.py` in the repo.
GGUF builds of `nvidia/LocateAnything-3B` for **locate-anything.cpp** - a C++/ggml inference engine for open-vocabulary detection / visual grounding, no Python at inference time. The detections are the same as the official PyTorch implementation (the engine is parity-gated against it), and it runs faster - on CPU and GPU. The full-precision `f32` GGUF (~15 GB) is reproducible from the HF weights with `scripts/convert_locateanything_to_gguf.py` in the repo.