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] Fixed stateful KV cache issues + minor improvements #21618

Conversation

vladimir-paramuzov
Copy link
Contributor

Details:

  • Fixed state initializer handling in shape inference of read_value primitive
  • Added an exception for shape_of subgraphs markup for read_value to terminate mark propagation for this node
  • Extended KV cache func tests for the cases with gather (from beam search) and state initializer subgraph
  • Added output partial shape parameter for broadcast to have better compile-time shape inference and less dynamic dimensions if ngraph was able to propagate part of the dimensions and make those static

@vladimir-paramuzov vladimir-paramuzov added the category: GPU OpenVINO GPU plugin label Dec 13, 2023
@vladimir-paramuzov vladimir-paramuzov added this to the 2023.3 milestone Dec 13, 2023
@vladimir-paramuzov vladimir-paramuzov requested review from a team as code owners December 13, 2023 07:49
@vladimir-paramuzov vladimir-paramuzov merged commit 2bcc940 into openvinotoolkit:master Dec 13, 2023
75 checks passed
@vladimir-paramuzov vladimir-paramuzov deleted the stateful_improvements branch December 13, 2023 12:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: GPU OpenVINO GPU plugin
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants