Support MoVA models and live weight sync - #86
Draft
akhauriyash wants to merge 5 commits into
Draft
Conversation
Convert gated dense and routed-value attention tensors into the canonical xLLM inference layout. Keep MoVA value experts on attention TP rather than FFN expert parallelism, synchronize router bias buffers, and reject stale cache-preserving updates.
Register the MoVA and xLLM router CLI contract in Miles and select Megatron's MoVA config and heterogeneous block spec whenever value experts are enabled. Fail early on incompatible provider, checkpoint-conversion, and attention settings while preserving the ordinary Transformer provider unchanged.
Add a cheap opt-in acceptance check that queries every rollout engine after each synchronization. Keep the existing random CI sample as the default and avoid full tensor comparisons.
Include the upstream K3 estimator before pinning the acceptance image. Resolve the shared argument-test addition by retaining both MoVA and K3 coverage.
Weight-version metadata must never advance after a failed or timed-out RDMA write. Drain every submitted transfer, clear the queue reliably, and surface aggregate failures to abort the update before rollout resumes.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
MoVATransformerConfigand the MoVA decoder specification for actor, reference, and old-actor models.Why
MoVA rollouts must preserve training/inference forward semantics while retaining SGLang's communication-free output-sharded value projection during decode.
Validation
prod, including current K3 coverage.