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.

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

Improve the performance of GMC router #356

Merged
merged 2 commits into from
Aug 28, 2024

Conversation

zhlsunshine
Copy link
Collaborator

Description

Improve the performance of GMC router by:

  1. Define the custom transport
  2. Re-use the http.Client with custom transport

Issues

n/a.

Type of change

List the type of change like below. Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds new functionality)
  • Breaking change (fix or feature that would break existing design and interface)

Dependencies

n/a.

Tests

No change for use case and scenario.

Copy link
Collaborator

@irisdingbj irisdingbj left a comment

Choose a reason for hiding this comment

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

If we can have some performance data comparison, it will be better.

@zhlsunshine
Copy link
Collaborator Author

If we can have some performance data comparison, it will be better.

Hi @irisdingbj, how about to add this in the task list? Or we can pick cherry this as release 0.9?

@KfreeZ
Copy link
Collaborator

KfreeZ commented Aug 28, 2024

issue #338 #258 related
if this PR can fix the issues, please also revert the PR opea-project/GenAIExamples#646

@zhlsunshine
Copy link
Collaborator Author

issue #338 #258 related if this PR can fix the issues, please also revert the PR opea-project/GenAIExamples#646

Hi @KfreeZ, thanks for the information!

@zhlsunshine
Copy link
Collaborator Author

Hi @irisdingbj, I added the milestone 0.9 and 1.0 to this PR, then we may do the performance test based on milestone 0.9

@zhlsunshine
Copy link
Collaborator Author

issue #338 #258 related if this PR can fix the issues, please also revert the PR opea-project/GenAIExamples#646

Hi @KfreeZ, I have test manually based on your opea-project/GenAIExamples#646 in the Xeon node with model meta-llama/CodeLlama-7b-hf, below is the output:

image
image

@KfreeZ
Copy link
Collaborator

KfreeZ commented Aug 28, 2024

issue #338 #258 related if this PR can fix the issues, please also revert the PR opea-project/GenAIExamples#646

Hi @KfreeZ, I have test manually based on your opea-project/GenAIExamples#646 in the Xeon node with model meta-llama/CodeLlama-7b-hf, below is the output:

image image

appreciate it, thank you @zhlsunshine !!!

@daisy-ycguo daisy-ycguo merged commit 68a2011 into opea-project:main Aug 28, 2024
7 checks passed
@lianhao lianhao mentioned this pull request Sep 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants