NVIDIA / NVIDIA/CUDALibrarySamples

nvcompBatchedZstdCompressGetTempSizeAsync returns monstrous temp buffer sizes

Open
#291 2 comments 0 reactions 1 assignee View on GitHub

@naveenaero is already working on this.

Since Oct 24, 2025.

nvCOMP
Dominant language
Cuda
Stars
2.5k
Forks
478
No merged PRs in 30d

Description

[reposting here because I originally missed the instruction in the legacy nvcomp repo to post issues here instead]

nvcompBatchedZstdCompressGetTempSizeAsync returns giant values for temp_bytes, no matter the size of the input data. Even if only 4 bytes are being compressed, the temp buffer size returned will be around 500mb.

Surely a temp buffer of that size isn't actually required for such a small chunk of data to compress?

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.