Add distributed tensor slice APIs for resharding workflows #121
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
Introduces put_slice() and get_slice() APIs to support distributed tensor storage and retrieval with explicit slice metadata. This enables efficient resharding between different parallelism strategies (e.g., FSDP to TP). Key changes: - Add put_slice() API for storing tensor shards with position metadata - Add get_slice() API for fetching specific slices from distributed tensors - Add LocalClient.put_slice() implementation - Add test_slice_api.py with comprehensive slice API tests - Export slice APIs in torchstore.__init__ These APIs work with the existing transport system and will benefit from GPU-direct transports like CUDA IPC when available. Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
meta-cla
bot
added
the
CLA Signed
This was referenced Feb 7, 2026
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Outdated suggestions cannot be applied.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.
Introduces put_slice() and get_slice() APIs to support distributed tensor storage and retrieval with explicit slice metadata. This enables efficient resharding between different parallelism strategies (e.g., FSDP to TP).
Key changes:
These APIs work with the existing transport system and will benefit from GPU-direct transports like CUDA IPC when available.