Draft
Conversation
5 tasks
Explain how domains, imported opsets, schemas, and attributes define node contracts. Document Mobius's opset-24 static-cache requirements and TensorRT parser portability risks. Signed-off-by: GitHub <noreply@github.com> Co-authored-by: rui-ren <15321482+rui-ren@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Explain domains, opsets, schemas, and attributes in ONNX nodes
Document ONNX operator contracts for TensorRT
Sep 4, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ONNX node semantics depend on the operator name, domain, imported opset, and schema. This adds Day 2 notes connecting those contracts to Mobius’s opset-24 requirements and TensorRT compatibility.
Operator semantics
Mobius Attention contract
nonpad_kv_seqlenas tensor input index6.q_num_heads,kv_num_heads,scale, andis_causalas attributes.Opset lowering
TensorScatterand populated Attention input6prevent safe lowering to opset 23.TensorRT portability