Skip to content

openvino: Update to OV 2026.2.1, self-contained release packages, operator improvements - #24974

Merged
ggerganov merged 10 commits into
ggml-org:masterfrom
ravi9:dev_backend_openvino
Jun 26, 2026
Merged

ggerganov merged 10 commits into
ggml-org:masterfrom
ravi9:dev_backend_openvino

Conversation

@ravi9

@ravi9 ravi9 commented Jun 24, 2026

Copy link
Copy Markdown
Contributor

Overview

  • Update OpenVINO to 2026.2.1.
  • Add OpenVINO self-contained release packages
  • Remove hardcoded compute_op_type sets for cleaner op dispatch
  • Enable softmax with sink input
  • Optimize mul_mat_id convert process for large sizes
  • Support 2D/4D in add_id
  • Add glu_swiglu_oai operator

Requirements

@ravi9
ravi9 requested review from a team and ngxson as code owners June 24, 2026 13:50
@github-actions github-actions Bot added documentation Improvements or additions to documentation devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning OpenVINO labels Jun 24, 2026
Comment thread .github/workflows/release.yml Resolved
Comment thread .github/workflows/release.yml Resolved
@ravi9

ravi9 commented Jun 24, 2026

Copy link
Copy Markdown
Contributor Author

Thank you @CISC for the quick review. Updated.

Comment thread .github/workflows/release.yml Resolved

@CISC CISC left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Please show successful release on your fork.

@ravi9

ravi9 commented Jun 24, 2026

Copy link
Copy Markdown
Contributor Author

Please show successful release on your fork.

Here it is: https://github.com/ravi9/llama.cpp/actions/runs/28129734793

@ravi9

ravi9 commented Jun 25, 2026

Copy link
Copy Markdown
Contributor Author

@taronaeo could you kindly review this PR.

@ravi9

ravi9 commented Jun 25, 2026

Copy link
Copy Markdown
Contributor Author

@ggerganov could you kindly review this PR.

@ggerganov
ggerganov merged commit 5397c36 into ggml-org:master Jun 26, 2026
22 of 27 checks passed
adrianhoehne pushed a commit to adrianhoehne/llama.cpp that referenced this pull request Jul 5, 2026
…rator improvements (ggml-org#24974)

* Update to OV 2026.2.1, Make OV release packages self-contained

* Update to OV 2026.2.1, Make OV release packages self-contained

* OpenVINO Backend: Remove compute_op_type hardcoded sets (ggml-org#222)

* OpenVINO Backend: Remove compute_op_type hardcoded sets

* revert get_op_type removal

* OpenVINO backend: enable softmax with sink input

* OpenVINO backend: opt mul_mat_id convert process for large size

* OpenVINO backend: Modify add_id to support 2D/4D

* OpenVINO Backend: Add glu_swiglu_oai

* PR review: fix paths

* PR review: fix path consistency

---------

Co-authored-by: Mostafa <mostafas.main.email@gmail.com>
Co-authored-by: Xuejun <Xuejun.Zhai@intel.com>
zommiommy pushed a commit to zommiommy/llama.cpp that referenced this pull request Aug 18, 2026
…rator improvements (ggml-org#24974)

* Update to OV 2026.2.1, Make OV release packages self-contained

* Update to OV 2026.2.1, Make OV release packages self-contained

* OpenVINO Backend: Remove compute_op_type hardcoded sets (ggml-org#222)

* OpenVINO Backend: Remove compute_op_type hardcoded sets

* revert get_op_type removal

* OpenVINO backend: enable softmax with sink input

* OpenVINO backend: opt mul_mat_id convert process for large size

* OpenVINO backend: Modify add_id to support 2D/4D

* OpenVINO Backend: Add glu_swiglu_oai

* PR review: fix paths

* PR review: fix path consistency

---------

Co-authored-by: Mostafa <mostafas.main.email@gmail.com>
Co-authored-by: Xuejun <Xuejun.Zhai@intel.com>
zbrad pushed a commit to zbrad/llama.cpp that referenced this pull request Sep 10, 2026
…rator improvements (ggml-org#24974)

* Update to OV 2026.2.1, Make OV release packages self-contained

* Update to OV 2026.2.1, Make OV release packages self-contained

* OpenVINO Backend: Remove compute_op_type hardcoded sets (ggml-org#222)

* OpenVINO Backend: Remove compute_op_type hardcoded sets

* revert get_op_type removal

* OpenVINO backend: enable softmax with sink input

* OpenVINO backend: opt mul_mat_id convert process for large size

* OpenVINO backend: Modify add_id to support 2D/4D

* OpenVINO Backend: Add glu_swiglu_oai

* PR review: fix paths

* PR review: fix path consistency

---------

Co-authored-by: Mostafa <mostafas.main.email@gmail.com>
Co-authored-by: Xuejun <Xuejun.Zhai@intel.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

devops improvements to build systems and github actions documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning OpenVINO

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants