Update CI docker image and set vllm eager enforce_eager to False#614
Merged
chtruong814 merged 11 commits intomainfrom Feb 23, 2026
Merged
Update CI docker image and set vllm eager enforce_eager to False#614chtruong814 merged 11 commits intomainfrom
chtruong814 merged 11 commits intomainfrom
Conversation
Signed-off-by: Charlie Truong <chtruong@nvidia.com>
chtruong814
requested review from
athitten,
meatybobby,
oyilmaz-nvidia and
pthombre
as code owners
Signed-off-by: Charlie Truong <chtruong@nvidia.com>
Signed-off-by: Charlie Truong <chtruong@nvidia.com>
Signed-off-by: Charlie Truong <chtruong@nvidia.com>
Signed-off-by: Charlie Truong <chtruong@nvidia.com>
ko3n1g
approved these changes
Feb 22, 2026
oyilmaz-nvidia
approved these changes
Feb 23, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Update CI docker image and set vllm eager enforce_eager to False
vllm checks if certain torch features are available based on the torch version. In particular, vllm 0.14.1 assumes 32 bit indexing is available for torch versions >= 2.10.0.dev. However, when installed in the 25.11 NGC Pytorch container, vllm believes that feature should work with the container's torch version. But this is not correct.
https://github.com/vllm-project/vllm/blob/v0.14.1/vllm/compilation/decorators.py#L524
So, this change updates the CI docker image with a patched version of vllm that does not treat the 25.11 NGC Pytorch version as >= 2.10.0.dev. We also previously set the VLLMExporter to default to enforce_eager=True. This change should enable enforce_eager=False.