[Blog] Fix redundant 'vllm serve' in DGX Spark Docker invocation - #305
Open
xinrub-droid wants to merge 1 commit into
Open
[Blog] Fix redundant 'vllm serve' in DGX Spark Docker invocation#305xinrub-droid wants to merge 1 commit into
xinrub-droid wants to merge 1 commit into
Conversation
Author
|
@zlxi02 Could you please take a look at this small doc fix? Thanks! |
The vllm/vllm-openai image entrypoint is already 'vllm serve', so specifying 'vllm serve' again in the docker run command results in 'vllm serve vllm serve <model>' which errors at startup. Remove the duplicate 'vllm serve' so the model name is passed directly as the argument to the entrypoint. Signed-off-by: Xinru Bao <xinrub@nvidia.com>
xinrub-droid
force-pushed
the
fix/remove-duplicate-vllm-serve-docker-cmd
branch
from
August 14, 2026 02:37
1b53991 to
159b0cb
Compare
Author
|
@ywang96 Could you please take a look at this small doc fix? Thanks! |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
The
vllm/vllm-openaiimage entrypoint is alreadyvllm serve, so theDocker command in the DGX Spark blog post was effectively running:
which errors at startup.
Fix
Remove the redundant
vllm servefrom thedocker runcommand so themodel name is passed directly as the argument to the entrypoint.