[Apache TVM Discuss] [Questions] Where can i find the source projects which generate the sample bit file

2020-09-08 Thread Lei Wang via Apache TVM Discuss
I'm a noob who just learn tvm for weeks, when i follow the book [**Get Started with VTA**](https://tvm.apache.org/docs/vta/tutorials/vta_get_started.html#sphx-glr-download-vta-tutorials-vta-get-started-py) with my pynq board, i notice that vta use rpc to program my borad with a sample bit str

[Apache TVM Discuss] [Application] LLVM target triple for Graviton2 CPUs

2020-09-08 Thread Cody H. Yu via Apache TVM Discuss
This is the one we used on EC2 m6g: `llvm -device=arm_cpu -mtriple=aarch64-linux-gnu -mattr=+v8.2a,+fullfp16,+fp-armv8,+dotprod,+crc,+crypto,+neon` --- [Visit Topic](https://discuss.tvm.apache.org/t/llvm-target-triple-for-graviton2-cpus/7829/5) to respond. You are receiving this because

[Apache TVM Discuss] [Questions] ResNet50 based one stage detector model conversion gets hung up

2020-09-08 Thread dexception via Apache TVM Discuss
Facing same issue. Able to reproduce using the following code: import os import numpy as np import nnvm.testing import nnvm.compiler import tvm import mxnet as mx from tvm import autotvm import tvm.relay as relay from tvm.autotvm.tuner import XGBTuner, GATune

[Apache TVM Discuss] [Application] LLVM target triple for Graviton2 CPUs

2020-09-08 Thread Giuseppe Rossini via Apache TVM Discuss
Hello @pratikfegade, This is what I always use (which also enables the dot-product support. If you don't want it, just remove the `+dotprod`): `"llvm -device=arm_cpu -mtriple=aarch64-linux-gnu -mattr=+neon,+v8.2a,+dotprod"` A good source for me was [this tutorial](https://tvm.apache.org/do

[Apache TVM Discuss] [Questions] ResNet50 based one stage detector model conversion gets hung up

2020-09-08 Thread james_bond via Apache TVM Discuss
This needs to be checked. Waiting for answers. --- [Visit Topic](https://discuss.tvm.apache.org/t/resnet50-based-one-stage-detector-model-conversion-gets-hung-up/2373/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click he

[Apache TVM Discuss] [Application] LLVM target triple for Graviton2 CPUs

2020-09-08 Thread Ramana Radhakrishnan via Apache TVM Discuss
-mcpu=neoverse-n1 should be fine depending on the version of llvm . I can't remember if you need anything in the -mattr to specifically allow for the dot product or fp16 . @giuseros has probably some experience here Ramana --- [Visit Topic](https://discuss.tvm.apache.org/t/llvm-targ

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

2020-09-08 Thread Dileep via Apache TVM Discuss
Hi @jacobpostman, After updating Xcode and iOS with the latest version also I'm facing the same issue. what version you are using Xcode and iOS version for tuning? Thanks, Dileep --- [Visit Topic](https://discuss.tvm.apache.org/t/auto-tvm-how-to-auto-tune-the-model-on-ios-device/7681/16

[Apache TVM Discuss] [Questions] Relay VM from C++

2020-09-08 Thread hsuan via Apache TVM Discuss
Hi, I am integrating vm with c++ api recently, does this example still work? I got segfault with `adtObj->size` --- [Visit Topic](https://discuss.tvm.apache.org/t/relay-vm-from-c/5623/7) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from the