There are at most (O(\log V)) rounds for (V) vertices (each round adds at least one edge per remaining tree in a connected component, and the number of trees shrinks). The implementation also supports ...
turboquant-py implements the TurboQuant and QJL vector quantization algorithms from Google Research (ICLR 2026 / AISTATS 2026). It compresses high-dimensional floating-point vectors to 1-4 bits per ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results