[Misc] Allow initializing KV cache transfer agent when using third-party library for disaggregated prefill #11480
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Outdated suggestions cannot be applied.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.
Allow initializing the KV cache transfer agent even when
kv_parallel_size==1
.This is because, when using third-party library for disaggregated prefill, it's possible that it handles everything in the library (and thus it does not need to set kv_parallel_size>1), but we still need to initialize the agent to initialize third-party connector in the first place.