tqchen commented on PR #20063: URL: https://github.com/apache/tvm/pull/20063#issuecomment-5124829180
Rebased this PR's three-commit series onto current `main@115029b3ab44c177bfca56c2c1bcf65566450d26`; the new exact head is `8c82011301213c409d961b8fff1c732215d09ae5`. Integration audit: - preserved the dependency-aware ConvertSSA buffer-remap invalidation added upstream and adapted it to `BufferVar`; - preserved the new logical element-pointer handling and now derives pointer dtype/storage scope from `BufferType`; - ported the three affected upstream tests to the typed-buffer representation. Validation completed on the rebased tree: - LLVM/CUDA compiler build and exact-head no-op rebuild; - exact `CI=true` H200 `docs/how_to/tutorials/optimize_llm.py` run with CUDA/NVRTC 13.1; - target-codegen suites: 804 passed, 32 skipped; - H200 TIRx CUDA + MLA: 16 passed, 155 skipped; - broad TIRx/S-TIR: 2,440 passed, 1,624 skipped, 10 xfailed, 2 xpassed. The sole failure was isolated to this build omitting the optional `runtime.RPCTimeEvaluator` RPC global, rather than a source regression; - repository-wide all-files pre-commit and `git diff --check`. The PR remains open and unmerged for fresh CI on the new exact head. -- 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]
