feat: render portable slurm serving lifecycle - #343
Closed
cquil11 wants to merge 1 commit into
Closed
Conversation
Contributor
Author
|
Closing because the project scope is now limited to porting active, nondeprecated AMD multi-node configurations to srt-slurm. This PR is outside that scope. |
Contributor
Author
|
Reopening: this PR predates the recent out-of-scope configuration-porting detour and was closed by mistake during an overly broad cleanup. Its prior state is being restored. |
Collaborator
|
Closing with the 2.0 merge (#407): the direct-host lifecycle this renders was removed, and 2.0 is Slurm only. The branch stays for a post-2.0 execution-target discussion. |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add
srtctl render-launch -f recipe.yamlto compile a resolved Dynamo/SGLang recipe into a portable Slurm serving script.The generated script discovers nodes and IPs from the active allocation, starts NATS/etcd, optional Mooncake infrastructure, workers, and the Dynamo frontend, waits for worker readiness, and cleans up the processes it owns. It uses the same command builders as normal execution without embedding a recorded job ID, hostname, IP address, endpoint, or secret value.
Usage
The initial scope is homogeneous Slurm allocations with the SGLang backend, a single Dynamo frontend, and no nginx. The artifact covers the serving lifecycle; benchmark, telemetry, and post-processing stages remain outside it.