arangasa opened a new pull request, #16415: URL: https://github.com/apache/tvm/pull/16415
…ay for Hexagon This is needed for supporting a new static memory planner which allocates a single storage object, and uses non-overlapping offset ranges within the storage object to allocate tensors. Allocating a storage object is an expensive operation involving OS, whereas tensor allocation (using AllocNDArray) is much less expensive. -- 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]
