vLLM is a fast and easy-to-use library for LLM inference and serving.
Last updated: 7 days agoA heterogeneous hardware acceleration library focused on efficient KV cache transfer operators (H2D/D2H), designed for large model training and inference scenarios.
Last updated: 19 days agoA heterogeneous hardware acceleration library focused on efficient KV cache transfer operators (H2D/D2H), designed for large model training and inference scenarios.
Last updated: 19 days agoLibrary targeting Intel Architecture for specialized dense and sparse matrix operations, and deep learning primitives.
Last updated: 1 month agoOpenCV means Intel® Open Source Computer Vision Library.
Last updated: 1 month agoIntel(R) Math Kernel Library for Deep Neural Networks
Last updated: 1 month ago