microsoft / microsoft/onnxruntime

[Documentation Request] Clarify do_copy_in_default_stream effect

Open
#11,913 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

documentation ep:CUDA
Dominant language
C++
Stars
21.9k
Forks
4.2k
Avg merge
4d 8h
Merged PRs (30d)
179

Description

Documentation on do_copy_in_default_stream is ambiguous as listed in https://onnxruntime.ai/docs/api/c/struct_ort_c_u_d_a_provider_options.html#a5186a856edeaf860dc547db309e85f95

It says: "Flag indicating if copying needs to take place on the same stream as the compute stream in the CUDA EP", however compute doesn't seem to necessarily happen in default stream. Unless flags for running computing in default stream are explicitly set (https://onnxruntime.ai/docs/api/c/struct_ort_c_u_d_a_provider_options.html#a2ca74dbd91996bad4a1c81af705a0ac7, https://onnxruntime.ai/docs/api/c/struct_ort_c_u_d_a_provider_options.html#a610a0511f8795bdd2b137f0138cfc88f), it might end up in a separate stream.

I believe it would be clearer if it just stated that when do_copy_in_default_stream is set, the copy happens in default stream.

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.

Research direction

Open the linked OrtCUDAProviderOptions API documentation and compare do_copy_in_default_stream with the two linked compute-stream options. Clarify the do_copy_in_default_stream description so it states when copying occurs on the default stream, then verify the linked API page shows the updated wording.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
documentation
Issue type
Documentation
Difficulty
1/5
Estimated time
Under an hour
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.