[TVM Discuss] [Questions] How to further improve the performance of given schedule?

cc @FrozenGene who might have some past experience in perf investigation --- [Visit Topic](https://discuss.tvm.ai/t/how-to-further-improve-the-performance-of-given-schedule/7711/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails,

[TVM Discuss] [Questions] Tensorize with non-divisible split factor

Hi @KireinaHoro, Since I am hitting the same issue, were you able to find a solution? Thanks, Giuseppe --- [Visit Topic](https://discuss.tvm.ai/t/tensorize-with-non-divisible-split-factor/6504/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe f

[TVM Discuss] [Questions] [Auto-TVM] How to Auto tune the model on iOS device

@kazum, @tqchen any suggestion on the above issue. Thanks --- [Visit Topic](https://discuss.tvm.ai/t/auto-tvm-how-to-auto-tune-the-model-on-ios-device/7681/5) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https:

[TVM Discuss] [Questions] CPU usage is very high on Android pad

Hi all, Recently, I deployed my model to Android pad. My cpu is cortext-a53 and aarch64. My model is CNN-based and only has 900k parameter. When I run it on my pad, I used the top to observe the cpu usage. I found it is very high. Does anyone have ideas about this problem? --- [Visit

[TVM Discuss] [Questions] Faster RCNN: CPU compilation with Relay VM takes long time

I am using an older version of TVM@a64feed. FasterRCNN was downloaded from here: http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_v2_coco_2018_01_28.tar.gz VM Compilation reaches ManifestAlloc stage within 5 minute. Since the graph becomes huge after this point, Fo