Per instance ere launch#1409
Draft
chetanyb wants to merge 3 commits into
Draft
Conversation
- Validate zkboost instances using the effective zkvm list that the launcher renders: per-instance zkvms when present, otherwise top-level zkvms. - Avoid injecting the default mock when any instance defines its own zkvms, fail early on duplicate proof types within a single rendered instance, and keep requested proof type plus ERE GPU validation aligned with the launcher behavior. - Add dry-run fixtures covering global zkvms, per-instance zkvms, default mock injection, duplicate proof types, missing requested proof types, and GPU overlap validation.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Known Limitations
Global
zkboost_params.zkvmsbackward compatibility: When multiple instances share a globalzkvmslist (no per-instance override), each instance now launches its own ere-server with the same GPU config. This will fail GPU exclusivity validation. Workaround: use per-instancezkvmswith distinctgpu.device_ids.This is a design tradeoff — global zkvms previously meant "one shared ere-server", now they mean "template copied per-instance". A follow-up could add explicit
shared: truesemantics if needed.Test plan
instances[N].zkvms[M]paths🤖 Generated with Claude Code