Skip to content

Add GQA support on OVEP GPU #813

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.

Sign up for GitHub

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

Draft
wants to merge 1 commit into
base: ovep-develop
Choose a base branch
from
Draft

Add GQA support on OVEP GPU #813

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions onnxruntime/core/providers/openvino/backends/basic_backend.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,7 @@ struct OnnxToOvNetworkBindings {
"beam_idx",
"past_key_values",
"present",
"total_seq_len",
};

OnnxToOvNetworkBindings(OVExeNetwork& exec_network, SubGraphContext& subgraph_context, SessionContext& session_context) {
Expand All @@ -72,15 +73,15 @@ struct OnnxToOvNetworkBindings {
// stateful representation has introduced these new tensors, creating a name mismatch (matched_names=false).
// So, if there is a name mismatch, or the name matches our special io list, we simply continue processing
// here to prevent runtime exceptions.
if (session_context.enable_causallm) {
//if (session_context.enable_causallm) {
if (!matched_names ||
std::any_of(special_io_names_.begin(), special_io_names_.end(),
[&onnx_name](const std::string& name) { return onnx_name.find(name) != std::string::npos; })) {
// This case also requires dynamic shape inference, so we'll mark the bindings as dynamic.
has_dynamic_io_ = true;
continue;
}
}
//}

ORT_ENFORCE(matched_names, log_tag,
"Input names mismatch between OpenVINO and ONNX. ", onnx_name,
Expand Down
1 change: 1 addition & 0 deletions onnxruntime/core/providers/openvino/ov_versions/data_ops.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,7 @@ std::vector<SupportedOp> supported_op_mode = {
{"Atanh", V_2020_4, {"CPU"}},
{"Atanh", V_2022_1, {"GPU"}},
{"Attention", V_2023_0, {"CPU", "GPU"}},
{"GroupQueryAttention", V_2023_0, {"CPU", "GPU"}},
{"AveragePool", V_2020_4, {"CPU", "GPU"}},
{"BatchNormalization", V_2020_4, {"CPU", "GPU"}},
{"BiasGelu", V_2023_0, {"CPU", "GPU"}},
Expand Down
Loading