1. TurboQuant in gguf-runner: roughly half the memory at nearly the same speed

    Implementing TurboQuant in gguf-runner cuts KV-cache memory roughly in half while staying close to Q8 throughput.

  2. gguf-runner updates: vision support, releases, and many small improvements

    gguf-runner gained vision support, ships GitHub release binaries, and received many usability and performance improvements.