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

FP8 support on NPU #462

Merged
merged 2 commits into from
Oct 1, 2024
Merged

FP8 support on NPU #462

merged 2 commits into from
Oct 1, 2024

Conversation

n1harika
Copy link

@n1harika n1harika commented Oct 1, 2024

Tested on PTL and LNL.
Added data types: FLOAT8E4M3FN and FLOAT8E4M3FNUZ.

@@ -281,6 +281,10 @@ void DataOps::populate_types_supported() {
std::make_pair(V_2020_4, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_INT64));
supported_types_npu_.insert(
std::make_pair(V_2021_1, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_FLOAT16));
supported_types_npu_.insert(
std::make_pair(V_2023_0, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_FLOAT8E4M3FN));

Choose a reason for hiding this comment

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

Change the version from V_2023_0 to V_2024_3 as its enabled only in latest OV.

@n1harika
Copy link
Author

n1harika commented Oct 1, 2024

I have changed the version

@preetha-intel
Copy link

LGTM

@preetha-intel preetha-intel merged commit 4db9fb0 into ovep-develop-lnl-1.2 Oct 1, 2024
12 of 16 checks passed
@preetha-intel preetha-intel deleted the niharika/fp8 branch October 1, 2024 12:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants