Gemma4 vllm fixes#227
Open
RobMulla wants to merge 4 commits into
Open
Conversation
Signed-off-by: Rob Mulla <rob.mulla@gmail.com>
Signed-off-by: Rob Mulla <rob.mulla@gmail.com>
Signed-off-by: Rob Mulla <rob.mulla@gmail.com>
karan
approved these changes
Apr 20, 2026
karan
reviewed
Apr 20, 2026
| - --seed=42 | ||
| # TODO: Update tensor-parallel-size to match the number of chips in your topology | ||
| - --tensor-parallel-size=8 | ||
| - --tensor-parallel-size=1 |
Collaborator
There was a problem hiding this comment.
Did you mean to set TP=1 (replicated) and not TP=2 (sharded)?
| nodeSelector: | ||
| cloud.google.com/gke-tpu-accelerator: tpu7x | ||
| cloud.google.com/gke-tpu-topology: 2x2x1 | ||
| cloud.google.com/gke-tpu-topology: 1x1x1 |
Contributor
There was a problem hiding this comment.
This is going to cause an issue given the nodepool is creating a 2x2x1:
gcloud container node-pools create ${NODEPOOL_NAME} \
--project=${PROJECT_ID} \
--location=${REGION} \
--node-locations=${ZONE} \
--num-nodes=1 \
--machine-type=tpu7x-standard-4t \
--cluster=${CLUSTER_NAME}
Contributor
There was a problem hiding this comment.
also 1x1x1 is not readily available to 3Ps - the gke team is still testing it for external use
Signed-off-by: Rob Mulla <rob.mulla@gmail.com>
RobMulla
force-pushed
the
gemma4-vllm-fixes
branch
from
6eb5da4 to
eaa3dc5
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fixes the Gemma 4 vLLM recipes for Ironwood (v7x) based on feedback.
Key Changes: