pytorch / pytorch/executorch

Use FQNs instead of hash for tensor/data names

Open
#15,560 0 comments 0 reactions 1 assignee View on GitHub

@lucylq is already working on this.

Since Nov 4, 2025.

Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

Currently XNNPACK and Vulkan hash tensors/data blobs and use that as the key for program-data separation.

This makes it difficult to perform weight-only updates, as the hash changes. Instead, use the FQN (fully qualified name) of the tensor as the key.

The FQN currently causes issues in a few areas:

  1. Quantized weights have the name overwritten by quant_param_{n}, or frozen_param_{n}, so we lose the FQN information
  2. XNNPACK weight cache is a singleton, so names may clash for different models.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.