wrkgn.
← All projects
Project record01 mention
Originally shared on Hacker News

Leone

Leone is a local LLM runtime that includes a CPU path used to verify its CUDA kernels.

Last shared
01 / Source history

Shared over time

Each entry reflects what was shared on that date. Details may have changed since then.

  1. Leone

    Leone is a local LLM runtime that includes a CPU path used to verify its CUDA kernels.

    Posted by @torsi0n · Original comment ↗

    “Working on my local LLM runtime Leone. It has a CPU path that verifies the CUDA kernels.”
    Links shared