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Outdated suggestions cannot be applied.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.
Motivation
Currently when running
sglang
in a multi-node configuration with infiniband andNCCL_DEBUG=INFO
, the logs will containThis means all-reduces will be performed over TCP instead of gpu RDMA. In the VLLM containers, they fix this by installing
libibverbs-dev
hereDoing so in
sglang
's docker container fixes this issue and greatly speeds up multi-node deployments.Modifications
Add
libibverbs-dev
to the installed dependencies in the Dockerfile.Checklist