Show HN: Reame – a CPU inference server that gets faster as it runs(github.com)
github.com
Show HN: Reame – a CPU inference server that gets faster as it runs
https://github.com/swellweb/reame
10 comments
Sick that you can get 2 arm cores and 12 GB ram for free at Oracle cloud, did not know that
You can actually get more. You have an amount of resources for ARM servers, if you allocate all of that to a single one you ger 24GB RAM and 4 vCPU.
Yeah but it's Oracle
If you have good luck perhaps. That tier of server is virtually always sold out
The persistent KV cache is interesting; I’d love to see how much of the speedup remains when requests share less structure.
If a prefix cache is good, why not keep it in primary mem?
looks really interesting
Why qwen 2.5 everywhere? Why not 3.5?
Because llms reflect qwen 2.5 heavily in training data, and that's who is giving the recommendations.
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.