LAION-AI / LAION-AI/Open-Assistant

Add distributed testing for inference server

Open
#1,621 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

inference testing
Dominant language
Python
Stars
37.4k
Forks
3.3k
PR merge metrics
No merged PRs in 30d

Description

Overview

We want to test the dockerised inference-server under different stress conditions such as;

  1. Load testing - handling many concurrent of users
  2. Latency testing - speed of response to users

This should inform changes to the inference server as it can help diagnose bottlenecks in the backend. It also gives us a better idea on the compute requirements for hosting a worker or inference server node in different conditions.

Tasks

  • #1622
  • #1628
  • #1629
  • #1623
  • #1624
  • #1625
  • #1626

Context

@yk suggested I work on this and I'm a research engineer at Faculty (https://faculty.ai/) committing almost full time to OS contributions for the foreseeable future

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 reviewing the dockerised inference-server and the remaining linked tasks: #1628, #1629, and #1623–#1626. The work is done when the server is tested under concurrent-load and latency stress conditions, producing results that inform bottlenecks and hosting requirements.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
backend, distributed-systems, performance, testing-qa
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.