spectrometerHBH opened a new pull request, #20081: URL: https://github.com/apache/tvm/pull/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. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
