Add shard metadata to TensorDescriptor for mixed TP#158
Draft
ishandhanani wants to merge 2 commits intomainfrom
Draft
Add shard metadata to TensorDescriptor for mixed TP#158ishandhanani wants to merge 2 commits intomainfrom
ishandhanani wants to merge 2 commits intomainfrom
Conversation
Extend WorkerMetadata with oneof backend_metadata supporting both NIXL (bytes) and TransferEngine (session_id string). Update all metadata backends (memory, redis, kubernetes, layered) and regenerate Python protobuf stubs for protobuf 5.x compatibility.
Adds full_shape, shard_dim, effective_tp_size, and shard_index to TensorDescriptor in p2p.proto. These fields enable target workers to compute byte-range overlaps when source and target have different tensor parallelism degrees (e.g., seed TP=2, target TP=4). Updates all backends (memory, redis, k8s), types, and Python stubs.
ishandhanani
force-pushed
the
ishan/transfer-engine-backend
branch
from
a9f1142 to
cfbe428
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
full_shape,shard_dim,effective_tp_size,shard_indextoTensorDescriptorinp2p.protoDepends on
Test plan
cargo build --release+cargo testpass