TransformerOptimus / SuperAGI

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
https://superagi.com/
MIT License
15.31k stars 1.84k forks source link

Local llm mutli-gpu support #1391

Closed rounak610 closed 8 months ago

rounak610 commented 8 months ago

Description

Added multi-gpu support in local llms feature Command to build without local llms: docker compose -f docker-compose.yaml up --build
Command to build with local llms: docker compose -f docker-compose-gpu.yml up --build

Related Issues

Solution and Design

Test Plan

Type of change

Checklist

CLAassistant commented 8 months ago

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you all sign our Contributor License Agreement before we can accept your contribution.
1 out of 2 committers have signed the CLA.

:white_check_mark: rounak610
:x: Ubuntu


Ubuntu seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
You have signed the CLA already but the status is still pending? Let us recheck it.

codecov[bot] commented 8 months ago

Codecov Report

Attention: 1 lines in your changes are missing coverage. Please review.

Comparison is base (ea2a0b6) 58.64% compared to head (c4e856a) 58.67%. Report is 4 commits behind head on main.

Files Patch % Lines
superagi/llms/openai.py 94.44% 0 Missing and 1 partial :warning:
Additional details and impacted files ```diff @@ Coverage Diff @@ ## main #1391 +/- ## ========================================== + Coverage 58.64% 58.67% +0.02% ========================================== Files 230 230 Lines 11199 11213 +14 Branches 1209 1212 +3 ========================================== + Hits 6568 6579 +11 - Misses 4292 4294 +2 - Partials 339 340 +1 ```

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.