The GitHub Actions job "Lint" on tvm.git/relax-onnx-gather-shape-dynamic-index has succeeded. Run started by GitHub user hamzaqureshi5 (triggered by yongwww).
Head commit for run: 44b2dff833f7a6893ee2e0e41bc3accec5a96785 / Hamza Qureshi <[email protected]> [Relax][Frontend][ONNX] Support dynamic index for Gather on shape The ONNX importer's Gather converter asserted that indices must be a constant whenever the data operand is a ShapeExpr, raising "Only constant indices supported for shape gather." for any runtime-computed index. Detection post-processing graphs such as FasterRCNN feed a dynamic index into a Gather whose data comes from a Shape node, so import failed before compilation could start. Keep the fast path for a single constant index, which resolves one dimension to a PrimValue and preserves shape-specialized handling downstream. Any other index (dynamic, or a constant selecting multiple dimensions) materializes the shape as an int64 tensor via shape_to_tensor and gathers from it at runtime, reusing the existing negative-index normalization. Adds a regression test that gathers a dimension out of a Shape result using a non-constant index, covering positive and negative indices, and checks it against onnxruntime. Fixes part of #19965. Report URL: https://github.com/apache/tvm/actions/runs/28944335412 With regards, GitHub Actions via GitBox --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
