[CB] [Minor] Add data-parallel to overall script#46490
Merged
Merged
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
remi-or
force-pushed
the
cb-distributed-overall
branch
from
83c6c34 to
b34710a
Compare
remi-or
changed the title
ArthurZucker
approved these changes
Jun 10, 2026
Contributor
|
CI Dashboard: View test results in Grafana |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds a data-parallel mode to the
continuous_batching_overall.pyscript that we use to benchmark the performance of CB across a range of use cases.Until now, the script did not allow to leverage all the GPUs on a node because it only supported TP: if a user wanted to run 16 benchmarks on a 8 GPUs node with the model on a single GPU, the 16 benchmarks ran on the same GPU, in order. Now each GPU will get 16 / 2 = 8 benchmarks if
--dp-size 8is passed (must be run withtorchrun). This drastically decreases the time needed to run the full benchmark suite ofc.