guan404ming opened a new pull request, #18447: URL: https://github.com/apache/tvm/pull/18447
## Related - #18429 ## Why - Previously only extracted upper bounds, discarding lower bound information - Enables better memory planning and optimization with full range [min, max] ## How - Extract both tir_var_lower_bound and tir_var_upper_bound from PyTorch `ExportedProgram.range_constraints` - Update C++ transforms (static_plan_block_memory.cc, adjust_matmul_order.cc) to use lower bounds - Default: lower=0 if not specified, upper=INT64_MAX if not specified -- 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]
