jacobpostman opened a new pull request #6438: URL: https://github.com/apache/incubator-tvm/pull/6438
When using manual reference counting, MTLBuffer purgeable state should be set before releasing. cc @tqchen Resolves most of the issue reported in issue (#6376) . Approx ~800KB memory leak still occurs when loading a new or reloading a model. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected]
