without explicitly setting the threadpool, multiple backend runtime instance control flow will share a same threadpool and execute the operator sequential,
you can reference this example https://discuss.tvm.apache.org/t/cpu-affinity-setting-of-pipeline-process-when-using-config-threadpool/12153/2?u=hjiang to make the different inference running in parallel. we also have pipeline executor to handle multiple backend parallel running requirement, please reference this tutorial (in progress https://github.com/apache/tvm/pull/11557) when these backend have data dependency. --- [Visit Topic](https://discuss.tvm.apache.org/t/is-it-possible-to-run-two-inference-models-concurrently-in-vta/12910/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/9ebadef5300a2eb2d54f64b3a3b8d356040fb9a12444c30ece8ec69c3618fd88).
