stan-dev / stan-dev/loo

LLM code optimizations

Open
#384 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
R
Stars
157
Forks
38
Avg merge
4d 16h
Merged PRs (30d)
2

Description

Debrief is a recent package which is (broadly) aimed to provide LLM's profiling information in a clear manner. They have a case study describing major performance benefits they observed by setting an LLM loose on a problem. I tried something similar in one of my packages and am looking to get some nice performance benefits (including decreased memory usage not captured by touchstone).

My prompt was more minimal than theirs: "I want you to use the profvis and debrief package to iteratively make improvements to the main, scanning functions. The workflow: profile with profvis, analyze with pv_print_debrief(), optimize, and repeat."

I think we should do the same thing here.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by identifying the package's main scanning functions, then profile them with profvis and analyze the results with debrief's pv_print_debrief(). The work is complete when iterative changes produce demonstrated performance or memory improvements, with the results documented for comparison.

Written by the indexing model from the issue text.

Assessment

Tech stack
r
Domain
performance
Issue type
Refactor
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.