2 matching pages, found in 11 ms

Ask StyxWritten on your GPU machine; takes a few seconds the first time.

  1. discuss.google.devhttps://discuss.google.dev › t › announcing-day-0-support-for-k… › 385392
    More about discuss.google.dev
    Announcing Day 0 support for Kimi K3 on Google Cloud - Community Articles - Google Developer forums

    Jul 28, 2026. … AI Hypercomputer recipes in github validate the end-to-end stack (accelerators, storage mount configurations, and model servers) on Google Cloud infrastructure. See the recipes on GitHub GKE with llm-d recipes …

    0 points
  2. discuss.google.devhttps://discuss.google.dev › t › accelerate-tpu-model-loading-w… › 374835
    More about discuss.google.dev
    Accelerate TPU model loading while saving RAM on GKE - Community Articles - Google Developer forums

    Jun 22, 2026. Accelerate TPU model loading while saving RAM on GKE Google Cloud Community Articles inference , cloud-tpu , googler-article Alexis_MacAskill June 22, 2026, 8:33pm 1 As large language models (LLMs) grow …

    0 points

Search for “github site:discuss.google.dev” on Google, or add !ddg, !w and other shortcuts to any search.