Gpu

3 open source tools found

llama.cpp

Lightweight, pure C/C++ LLM inference with minimal setup and top performance on any hardware.

High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).

If installed via brew: `brew uninstall llama.cpp`. Via nix: `nix profile remove llama.cpp`. For manual install, delete the executable and `~/.cache/llama.cpp`.

111.2kChecksum

AI Productivity

cupy

CuPy enables NumPy/SciPy code to run on GPU with minimal changes, providing massive speedups for array operations.

CuPy is a NumPy/SciPy-compatible array library for GPU-accelerated computing, offering drop-in replacement to run existing code on NVIDIA CUDA or AMD ROCm platforms.

Run pip uninstall cupy-cuda12x (replace with your package name) or conda remove cupy if installed via conda.

11.6kChecksum

Developer Tools

meshoptimizer

Makes 3D meshes smaller and faster to render; a free, lightweight alternative to Simplygon.

Mesh optimization library that reduces GPU rendering cost. Provides vertex cache, overdraw, and vertex fetch optimization. Open-source (MIT).

If installed via package manager (vcpkg, Conan), remove the package using the manager's command. If sources were added manually, delete the files and remove the include from your project.

8.0kChecksum