Our skippy library is a patch queue on top of llama that allows us to access int... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

i386 3 months ago | parent | context | favorite | on: Mesh LLM: distributed AI computing on iroh

Our skippy library is a patch queue on top of llama that allows us to access internal information, such as activations, and filter tensors on model load.

rao-v 3 months ago [–]

This really should be in the blogpost. It’s both useful info and basic courtesy to be explicit about which underlying inferencing engine you are using

sig_kill 3 months ago | [–]

We didnt post it, we use a library (iroh) who featured us - so we are here answering any Q’s instead :)

Consider applying for YC's Winter 2027 batch! Applications are open till November 2.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact