pytorch / pytorch/executorch

Sample logits on CUDA memory before copying out to CPU

Open
#16,156 0 comments 0 reactions 1 assignee View on GitHub

@larryliu0820 is already working on this.

Since Dec 9, 2025.

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

Description

🚀 The feature, motivation and pitch

For LLM/ASR models on ExecuTorch CUDA backend, we always copy logits to CPU memory, right after we exit CUDA delegate. Theoretically we can run sampler on CUDA and only copy the sampled result out. The other variant of this is to store the sampled result on CUDA until all the tokens are generated and dump all the results at once.

This requires all delegates and the sampler on the same CUDA stream, also some scratch memory allocated for sampler.

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

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.