Keep SparkGLM independent; make LLooM integration optional - #2
Merged
Merged
Conversation
SparkGLM's default installer should run independently. Use Docker and SSH for source builds, pinned model downloads, worker-first startup and owned-container lifecycle. Keep the existing LLooM-managed flow behind --lloom; it requires an existing LLooM installation and never installs the gateway. Both paths retain the measured NVFP4 settings, with latest EXL3 explicitly selectable. Provenance: - Copy the measured standalone-capable entrypoint byte-for-byte from https://github.com/Enntity/lloom at 2cc2f0df9ddcb1bb7fe60f7bd6934d2a9de1e4f2, preserving its MIT AND Apache-2.0 notice and the repository license ledger. This script invokes vLLM directly and contains no LLooM runtime dependency. Original work: - Standalone Docker/SSH orchestration, private-fabric binding, owned-container checks, source/default dispatch, optional integration documentation and command-parity tests. No numerical engine changes or new performance claims. Verification: - scripts/check.sh all passed, including measured per-rank argument parity, rejection of foreign container ownership, standalone default and optional LLooM dispatch. All 66 checksum-bound result bundles remain valid. GPU runtime was not restarted; the existing LLooM-managed appliance remains in service.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Keep SparkGLM standalone and make LLooM integration opt-in
SparkGLM's default installer should run independently. Use Docker and SSH for source builds, pinned model downloads, worker-first startup and owned-container lifecycle. Keep the existing LLooM-managed flow behind --lloom; it requires an existing LLooM installation and never installs the gateway. Both paths retain the measured NVFP4 settings, with latest EXL3 explicitly selectable.
Provenance:
Original work:
Verification: