5 comments

  • JPLeRouzic 36 minutes ago

    Thanks for sharing your work!

    Please how to select the model? I downloaded tinyLlama, put it in ./models, changed reame.conf but I get:

    (No such file or directory)

    Otherwise putting the model in /opt does not please me much, I fear to forget a model is there, if it is in reame folder its much easier to notice and manage.

  • ahepp an hour ago

    If a prefix cache is good, why not keep it in primary mem?

  • ohadkr 2 hours ago

    The persistent KV cache is interesting; I’d love to see how much of the speedup remains when requests share less structure.

  • tyzoid 2 hours ago

    Why qwen 2.5 everywhere? Why not 3.5?

    • TheGoddessInari 8 minutes ago

      Because llms reflect qwen 2.5 heavily in training data, and that's who is giving the recommendations.