[OVEP] [CVS-177257] Adding support for OV 2026.1 and Float8 precisions#991
Open
n1harika wants to merge 4 commits intoovep-developfrom
Open
[OVEP] [CVS-177257] Adding support for OV 2026.1 and Float8 precisions#991n1harika wants to merge 4 commits intoovep-developfrom
n1harika wants to merge 4 commits intoovep-developfrom
Conversation
ankitm3k
reviewed
Mar 25, 2026
| std::make_pair(V_2024_4, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_INT4)); | ||
| supported_types_cpu_.insert( | ||
| std::make_pair(V_2024_4, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_UINT4)); | ||
| supported_types_npu_.insert( |
There was a problem hiding this comment.
is this support only valid for npu only? what about cpu & gpu FP8 support?
MayureshV1
requested changes
Mar 25, 2026
MayureshV1
left a comment
MayureshV1
left a comment
There was a problem hiding this comment.
@n1harika . FP8 has 2 modes: E4M3 and E5M2. Please add support for both.
| std::make_pair(V_2024_4, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_INT4)); | ||
| supported_types_initializer_.insert( | ||
| std::make_pair(V_2024_4, ONNX_NAMESPACE::TensorProto_DataType::TensorProto_DataType_UINT4)); | ||
| supported_types_initializer_.insert( |
There was a problem hiding this comment.
@n1harika .. Please add support for E4M3 as well as E5M2.
ONNX FE support
Author
There was a problem hiding this comment.
Sure, added.
Just FYI, I haven't tested the E5M2 type as the model I have generated doesn't use it. There are also two other ONNX FP8 precisions- E4M3FNUZ and E5M2FNUZ, will add these when ONNX FE supports them.
n1harika
force-pushed
the
niharika/fp8_cpu
branch
from
aee3a66 to
38e7aad
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR introduces OV 2026.0 and 2026.1 to data_ops.cc and capability.cc, and adds Float8 precisions for CPU/NPU/GPU which have been enabled from this OV version.