Repository navigation
Fix A4X-Max Reflection Beam Dynamo recipes on the current lmsysorg/sglang:beam image - #287
Merged
Chris113113 merged 3 commits intoOct 16, 2026
Conversation
…ol and image digest
- Patch the one ServerArgs.get_model_config() call that ai-dynamo 1.5.1 makes
but SGLang f7473673dd removed (guarded; no-op on images that still have it).
- Add dynamo.nodeSelector to the chart and pass the node pool in the Beam
install commands so all workers share one NVLink domain.
- Pin lmsysorg/sglang:beam by digest and correct the Dynamo version note.
- Pass --set dynamo.namespace=${NAMESPACE}; note fixed resource names.
- Note to skip the platform install when Dynamo is already on the cluster.
- Fix disaggregated README log commands.
- Add expected AgentX results (c=32; c=96 and c=192 pending).
There was a problem hiding this comment.
Code Review
This pull request pins the SGLang runtime image to a specific digest, introduces a NODE_POOL variable and nodeSelector configuration to ensure workers share an NVLink domain, and adds a startup patch in the Helm chart to handle a breaking change in SGLang's ServerArgs. The review feedback recommends making the startup patch more robust by safely resolving the Python module spec and verifying the file exists before executing sed to prevent potential container crash loops.
joeywan-google
marked this pull request as ready for review
October 16, 2026 18:57
Chris113113
requested changes
Oct 16, 2026
- Startup patch: resolve dynamo.sglang.args safely and skip with a warning when it is missing, so set -e can't crash-loop the worker. - Take the Beam image from the values file; drop DYNAMO_IMAGE and the --set workload.image override from the Beam install commands. - Remove the image/patch notes, the troubleshooting entry, and the expected results tables from the READMEs.
Chris113113
approved these changes
Oct 16, 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
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.
Summary
I followed the A4X-Max Reflection Beam Dynamo recipes from #286 end to end on an 8-node GB300 node pool, both aggregated (
beam_high_int) and disaggregated 4P4D (beam_high_throughput). As written, workers crash at startup on the current image. This PR fixes that and makes the recipes safe on shared or multi-pool clusters.Changes
lmsysorg/sglang:beam(SGLangf7473673dd,ai-dynamo1.5.1) removedServerArgs.get_model_config(), butdynamo/sglang/args.pystill calls it (AttributeErrorat startup). The worker launch script patches that one call. It does nothing when the method exists, and skips with a warning if the module isn't found.beam_high_int.yamlandbeam_high_throughput.yaml. The Beam install commands take the image from the values file.dynamo.nodeSelectorchart value, applied to every Dynamo pod. The Beam install commands pass--set dynamo.nodeSelector."cloud\.google\.com/gke-nodepool"=${NODE_POOL}so all workers share one NVLink domain on clusters with more than one GB300 node pool.--set dynamo.namespace=${NAMESPACE}in the install commands, with a note that fixed resource names need one namespace per concurrent release.Testing
helm templatewith and withoutdynamo.nodeSelector, for both Beam values files and DeepSeekvalues_deepep.yaml.a4x-maxgpu-4g-metalnodes each, on Dynamo operator1.4.2. Both became Ready and served the README §4.3 AIPerf AgentX run atCONCURRENCY=32for 3600 s with 0 errors (agg 4,788 requests, disagg 4,750).