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

➕ Install peft for prompt adapter support #124

Closed
wants to merge 5 commits into from
Closed

Conversation

prashantgupta24
Copy link

@prashantgupta24 prashantgupta24 commented Aug 8, 2024

For allowing PEFT adapters to be loaded, we will need the peft library installed.

Upstream PR: vllm-project#8123

Copy link

openshift-ci bot commented Aug 8, 2024

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

Copy link

openshift-ci bot commented Aug 8, 2024

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: prashantgupta24

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@openshift-ci openshift-ci bot added the approved label Aug 8, 2024
@prashantgupta24 prashantgupta24 marked this pull request as ready for review August 8, 2024 18:23
@openshift-ci openshift-ci bot requested review from heyselbi and z103cb August 8, 2024 18:23
@prashantgupta24
Copy link
Author

/retest

@dtrifiro
Copy link

dtrifiro commented Aug 12, 2024

/lgtm

This pass after #126 #127 is merged

Copy link

openshift-ci bot commented Aug 12, 2024

New changes are detected. LGTM label has been removed.

Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
Dockerfile.ubi Outdated Show resolved Hide resolved
prashantgupta24 and others added 2 commits August 20, 2024 11:14
Signed-off-by: Prashant Gupta <prashantgupta@us.ibm.com>
@@ -180,6 +180,10 @@ RUN --mount=type=cache,target=/root/.cache/pip \
--mount=type=cache,target=/root/.cache/uv \
uv pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp311-cp311-linux_x86_64.whl

# Install peft for prompt adapter support

Choose a reason for hiding this comment

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

Sorry if I get back to this, but I just realized this is something which is only supported in the adapter, right? In that case this should be a dependency in vllm-tgis-adapter and not something installed here.

Copy link
Author

Choose a reason for hiding this comment

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

This is something that is needed by vllm explicitly -

from peft.utils import load_peft_weights

Copy link
Author

@prashantgupta24 prashantgupta24 Aug 21, 2024

Choose a reason for hiding this comment

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

Also see these lines within PromptAdapterConfig:

vllm/vllm/config.py

Lines 1334 to 1340 in 7a21f52

library_name = 'peft'
try:
__import__(library_name)
except ImportError as e:
raise ImportError(
f"'{library_name}' is not installed for prompt adapter support."
f"Please install it using 'pip install {library_name}'."

Choose a reason for hiding this comment

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

I can confirm that this is needed to run the upstream unit tests.

@prashantgupta24
Copy link
Author

Will try to get it merged in upstream https://github.com/vllm-project/vllm/pull/8123/files

prarit pushed a commit to prarit/vllm that referenced this pull request Oct 18, 2024
* add memory clean up after every shape and parameter to reduce cache invalidation buffers

* small typo

* syntax change

---------

Co-authored-by: maleksan85 <maleksan@amd.com>
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.

3 participants