Lunderberg commented on PR #14320: URL: https://github.com/apache/tvm/pull/14320#issuecomment-1482890860
Fixed a couple of CI errors, re-running to see what occurs next. 1. Explicitly call `value.same_as(known_value)`, because `value in value_stack` would attempt to call `PrimExpr.__bool__(value == value_stack[0])`, which is not implemented. 2. Update cuda tensor intrinsic which introduced a variable binding between a `T.block()` and `T.reads()`. Using `name = T.meta_var(expr)` instead of `name = expr` follows the previous behavior of a variable rename, but done explicitly in the function definition. 3. Merged main into the PR branch to resolve conflict. (I also opened https://github.com/apache/tvm/pull/14399, to improve an error message encountered while debugging (2).) -- 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]
