The GitHub Actions job "tvm-bot" on tvm.git/main has succeeded.
Run started by GitHub user tqchen (triggered by tqchen).

Head commit for run:
4a09f4ef410e96c9dea1de26c3183dacdda5d753 / Bohan Hou <[email protected]>
[TIRx] Flatten cuda/trn backend operator folder (#20081)

## Summary

Flatten the CUDA/TRN backend Python layout by removing the pass-through
`operator` package layer:

- `tvm.backend.cuda.operator.intrinsics` → `tvm.backend.cuda.intrinsics`
- `tvm.backend.cuda.operator.tile_primitive` →
`tvm.backend.cuda.tile_primitive`
- `tvm.backend.trn.operator.tile_primitive` →
`tvm.backend.trn.tile_primitive`

The `operator` package was an empty shell: its `__init__.py` only
re-exported its subpackages, it added a meaningless path segment, and it
shadowed the stdlib `operator` name. No compatibility shim is kept; all
in-repo imports (source, tests, docs) are rewritten, and the
`tvm.tirx.<backend>.*` alias redirect picks the new paths up
automatically. Cross-package references inside the moved packages are
relative imports that resolve unchanged after the one-level move.

Companion kernel-side PR: mlc-ai/tirx-kernels#13.

## Test

Full TIRx suite on 8x B200 (16 xdist workers): `2620 passed, 41 skipped,
3 xpassed` in 386s; `bench_suite --check-imports` and `registry --cc 10
--strict` import gates green; `pre-commit` green.

Report URL: https://github.com/apache/tvm/actions/runs/30773020348

With regards,
GitHub Actions via GitBox


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to