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

Align HPU parameters with docker compose #528

Merged
merged 1 commit into from
Nov 8, 2024

Conversation

yongfengdu
Copy link
Collaborator

@yongfengdu yongfengdu commented Nov 7, 2024

Description

Align parameters with docker compose version

Issues

Fixes #499, Fixes #487, Fixes #530

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

List the newly introduced 3rd party dependency if exists.

Tests

Helm install

Copy link
Contributor

@eero-t eero-t left a comment

Choose a reason for hiding this comment

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

ChatQnA guardrails is also using rerank, so limits need to be increased for that too:
https://github.com/opea-project/GenAIInfra/blob/main/helm-charts/chatqna/guardrails-gaudi-values.yaml

And shouldn't the other updates from docker compose files be applied there too?

After that, commit & PR could state that it fixes also #487.

PS. GitHub Actions complaint could be fixed just by removing the commented out probes alternative, as it will remain in Git history.

helm-charts/chatqna/gaudi-values.yaml Show resolved Hide resolved
@lianhao
Copy link
Collaborator

lianhao commented Nov 8, 2024

@yongfengdu Since you're syncing between GenAIExamples and GenAIInfra, could you please address the issue #530 in this same PR at the same time? Thanks!

There is another guardrail-gaudi-values.yaml in chatqna which may need to be modified too

@lianhao lianhao added this to the v1.1 milestone Nov 8, 2024
Copy link
Collaborator

@lianhao lianhao left a comment

Choose a reason for hiding this comment

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

Also we need to enable ci-gaudi test for teirerank too

helm-charts/chatqna/gaudi-values.yaml Outdated Show resolved Hide resolved
Copy link
Collaborator

@Ruoyu-y Ruoyu-y left a comment

Choose a reason for hiding this comment

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

LGTM

@yongfengdu yongfengdu merged commit cb0bd53 into opea-project:main Nov 8, 2024
17 checks passed
NeoZhangJianyu pushed a commit to NeoZhangJianyu/GenAIInfra that referenced this pull request Nov 8, 2024
Signed-off-by: Dolpher Du <dolpher.du@intel.com>
Signed-off-by: ZhangJianyu <zhang.jianyu@outlook.com>
Signed-off-by: Dolpher Du <dolpher.du@intel.com>
@yongfengdu yongfengdu deleted the hputuning branch November 12, 2024 04:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
5 participants