Skip to content
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.

Sign up for GitHub

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

Preliminary benchmarking #185

Merged
merged 4 commits into from
Nov 13, 2023
Merged

Preliminary benchmarking #185

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3d430d4
Update README.md
richard-rogers Nov 10, 2023
10a3d7d
Update README.md
richard-rogers Nov 10, 2023
08ee228
pre-commit
richard-rogers Nov 10, 2023
122923b
Update README.md
richard-rogers Nov 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,6 +65,21 @@ More examples are available [here](https://github.com/whylabs/langkit/tree/main/

You can have more information about the different modules and their metrics [here](https://github.com/whylabs/langkit/blob/main/langkit/docs/modules.md).

## Benchmarks

| AWS Instance Type | Metric Module | Throughput |
|-------------------|:-------------:|----------------:|
| c5.xlarge | Light metrics | 2335 chats/sec |
| | LLM metrics | 8.2 chats/sec |
| | All metrics | 0.28 chats/sec |

| | | |
|-------------------|:-------------:|----------------:|
| p3.2xlarge | Light metrics | 1800 chats/sec |
| | LLM metrics | 9.8 chats/sec |
| | All metrics | 0.32 chats/sec |
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's validate the GPU flavors of dependency closure for the p3. Might try with g4dn.xlarge instances since those latest supported types in the Databricks ML GPU runtimes

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's remove the GPU rows until we can investigate their behavior further, the c5.xlarge rows are still useful as a start



## Frequently Asked Questions

You can check some frequently asked questions on our [FAQs section](https://github.com/whylabs/langkit/blob/main/langkit/docs/faq.md)
Loading