-
Notifications
You must be signed in to change notification settings - Fork 13
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Script for LLM benchmark - Humaneval #61
base: master
Are you sure you want to change the base?
Conversation
6c48b2e
to
1b408e0
Compare
54666a7
to
0d01f84
Compare
@@ -0,0 +1,27 @@ | |||
# How to Run the LLM benchmark - Inference workload |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you please add some description of the workload and references to it
human-eval-benchmark/Readme.md
Outdated
|
||
## 1. Using the Workbench | ||
## Pre-requisite | ||
As of now the user needs to have access to openshift AI cluster, create a Data Science project and setup a workbench with the following configuration |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you elaborate on openshift AI cluster. For example, an OCP cluster with GPU nodes and 'xyz' operator installed
human-eval-benchmark/Readme.md
Outdated
Towards the end of the script B the user is prompted to fill the run duration, which is for how long the user wants to apply load or keep the model running, by default its set to 1hr (3600 sec). | ||
|
||
## 2. Automated Job | ||
In this approach we already have a combined script named `script.py`, and a Docker file which is used to create this docker image `quay.io/kruizehub/human-eval-deployment` whcih is used in the `job.yaml` file. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fix whcih typo
human-eval-benchmark/Readme.md
Outdated
Towards the end of the script B the user is prompted to fill the run duration, which is for how long the user wants to apply load or keep the model running, by default its set to 1hr (3600 sec). | ||
|
||
## 2. Automated Job | ||
In this approach we already have a combined script named `script.py`, and a Docker file which is used to create this docker image `quay.io/kruizehub/human-eval-deployment` whcih is used in the `job.yaml` file. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is the namespace created as part of the job or user needs to create it?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
In my case it was already created
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You need to update the readme to create the namespace
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
added! can u re review
This pr contains a wip script for evaluating llm benchamrk.