Hi,
I am trying to integrate mxnet model in Sanic asynchronous application and am encountering a memory leak when running the model in run_in_executor. Have tried ctx.empty_cache() and mx.nd.waitall() and still, the leak persists when parallelizing the requests sent to the application. I am relatively new to mxnet and any help would be appreciated. --- [Visit Topic](https://discuss.mxnet.apache.org/t/gpu-memory-leak-with-sanic/6643/1) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.mxnet.apache.org/email/unsubscribe/9b0cf6e2adc258d1ee5e7a9a7a3beb63c119dfed6dcf6406f91f774cbbeb5224).
