gemini-code-assist[bot] commented on code in PR #18538: URL: https://github.com/apache/tvm/pull/18538#discussion_r2579483565
########## docs/how_to/tutorials/e2e_opt_model.py: ########## @@ -113,12 +113,14 @@ # We skip this step in the CI environment. if not IS_IN_CI: + with target: + mod = tvm.tir.transform.DefaultGPUSchedule()(mod) Review Comment:  For consistency with the `target` object defined earlier and used in this context, it's better to use it in the `tvm.compile` call on the next line as well, instead of the string `"cuda"`. This ensures that the most specific target information is used throughout the compilation process, which can lead to better optimizations. Consider changing line 118 to: ```python ex = tvm.compile(mod, target=target) ``` -- 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]
