From 2e220436be5e145459fd647543376a67a6fb5ba1 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Thu, 5 Feb 2026 22:43:28 +0000 Subject: [PATCH 1/2] Initial plan From 7bbcaf17fd34704a81ff47f73bd467e629b8ab88 Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Thu, 5 Feb 2026 22:48:08 +0000 Subject: [PATCH 2/2] Mark GroupQueryAttention as supported on CPU and GPU for OpenVINO EP Co-authored-by: MayureshV1 <47039074+MayureshV1@users.noreply.github.com> --- onnxruntime/core/providers/openvino/ov_versions/data_ops.cc | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/onnxruntime/core/providers/openvino/ov_versions/data_ops.cc b/onnxruntime/core/providers/openvino/ov_versions/data_ops.cc index b2fc34eab524f..a5eeffc362e2b 100644 --- a/onnxruntime/core/providers/openvino/ov_versions/data_ops.cc +++ b/onnxruntime/core/providers/openvino/ov_versions/data_ops.cc @@ -77,7 +77,7 @@ std::vector supported_op_mode = { {"Atanh", V_2020_4, {"CPU"}}, {"Atanh", V_2022_1, {"GPU"}}, {"Attention", V_2023_0, {"CPU", "GPU"}}, - {"GroupQueryAttention", V_2025_1, {"GPU"}}, + {"GroupQueryAttention", V_2025_1, {"CPU", "GPU"}}, {"AveragePool", V_2020_4, {"CPU", "GPU"}}, {"BatchNormalization", V_2020_4, {"CPU", "GPU"}}, {"BiasGelu", V_2023_0, {"CPU", "GPU"}}, @@ -382,6 +382,7 @@ void DataOps::populate_op_mode_supported() { no_dimension_supported_.push_back({"Sub", V_2020_4, {"All"}}); no_dimension_supported_.push_back({"Unsqueeze", V_2020_4, {"All"}}); no_dimension_supported_.push_back({"Where", V_2021_2, {"All"}}); + no_dimension_supported_.push_back({"GroupQueryAttention", V_2025_1, {"All"}}); subgraph_supported_.push_back({"Cast", V_2020_4, {"All"}}); subgraph_supported_.push_back({"Concat", V_2020_4, {"All"}});