[PD Feature] Support TP16 and Optimize Dynamic Connection Establishment #5354
Conversation
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
6 tasks
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Outdated suggestions cannot be applied.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.
[PD Feature] Support TP16 and Optimize Dynamic Connection Establishment
Motivation
Currently, Mooncake requires enhancements in handling multi-node
prefillanddecodesetups. Specifically, it needs to support dynamic connection establishment and work reliably with multi-node TP=16 scenarios.Thanks the pr: 5351 authored by @yuan-luo
Modifications
prefill_addrto bothprefillanddecodenodes. This address is now used as a key to register and query the corresponding IP and ZMQ port information.Checklist
prefill_addrforwarding and registration logic added