Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[GPU] Fix beam search accuracy/functional errors #27835

Merged

Conversation

sshlyapn
Copy link
Contributor

Details:

  • Fixed "error set arg" error caused by not initialized internal memory buffers required for indirect sdpa_opt kernel in case of micro_sdpa + sdpa_opt
  • Fixed beam_table offset in shape_info
  • Fixed beam table index calculation in rearrange_cache() call considering concat_axis
  • Backport of [GPU] Fix beam search accuracy/functional errors #27833

@sshlyapn sshlyapn added category: GPU OpenVINO GPU plugin Code Freeze labels Nov 29, 2024
@sshlyapn sshlyapn added this to the 2024.6 milestone Nov 29, 2024
@sshlyapn sshlyapn requested review from a team as code owners November 29, 2024 16:06
Copy link
Contributor

@p-durandin p-durandin left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

backport approved

@p-durandin p-durandin added this pull request to the merge queue Dec 4, 2024
@p-durandin p-durandin removed this pull request from the merge queue due to a manual request Dec 4, 2024
@p-durandin p-durandin added this pull request to the merge queue Dec 4, 2024
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to a conflict with the base branch Dec 4, 2024
@p-durandin p-durandin added this pull request to the merge queue Dec 4, 2024
Merged via the queue into openvinotoolkit:releases/2024/5 with commit e042531 Dec 4, 2024
150 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: GPU OpenVINO GPU plugin Code Freeze
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants