[TVM Discuss] [Questions] [relay]What does the mistake mean? “in particular dimensio 2 conflicts 3 does not match 2

My model is in the Intranet and cannot be taken out.Any good Suggestions and methods to check errors? --- [Visit Topic](https://discuss.tvm.ai/t/relay-what-does-the-mistake-mean-in-particular-dimensio-2-conflicts-3-does-not-match-2/6149/4) to respond. You are receiving this because you e

[TVM Discuss] [Questions] Arm cpu performance is too slow than mali gpu

Thank you Robert! This is really useful information. Thank you. --- [Visit Topic](https://discuss.tvm.ai/t/arm-cpu-performance-is-too-slow-than-mali-gpu/6220/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https

[TVM Discuss] [Questions] Arm cpu performance is too slow than mali gpu

Hi! Does this appear because of this previous issue: https://discuss.tvm.ai/t/bug-arm-significant-performance-degradation-of-execution-times-between-tvm-revisions/6029/ I was experiencing a similar slowdown on ARM CPUs which was lead back by the limited Winograd algorithm... Cheers Robert

[TVM Discuss] [Questions] [ TOPI ] Winograd convolution performance is too slow

Hi, I am now trying to use AutoTVM to tune the templates for different operators, but I do not know where exactly those templates which are already implemented by tvm are. Could you help me on this? Also, are there any examples or tutorials on how to use these templates? And from the Tuning H

[TVM Discuss] [Questions] Error in contructing IRModule from Relay c++ APIs

Trying to mimic tests/cpp/relay_build_module_test.cc in construct a simple Dense + Relu + Add function as below. ``` auto tensor_type_f32_16_8 = relay::TensorType({16, 8}, DataType::Float(32)); auto tensor_type_f32_8_8 = relay::TensorType({8, 8}, DataType::Float(32)); auto a = relay::Var

[TVM Discuss] [Questions] [Auto TVM][CUDA] tune_graph is possible in cuda?

No, it's not available for cuda. --- [Visit Topic](https://discuss.tvm.ai/t/auto-tvm-cuda-tune-graph-is-possible-in-cuda/6219/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscr

[TVM Discuss] [Questions] [relay]What does the mistake mean? “in particular dimensio 2 conflicts 3 does not match 2

this must be problem with shape of array where it can't reshape to target shape, may be you can attached model i can have a look into that --- [Visit Topic](https://discuss.tvm.ai/t/relay-what-does-the-mistake-mean-in-particular-dimensio-2-conflicts-3-does-not-match-2/6149/3) to respond.

[TVM Discuss] [Questions] Arm cpu performance is too slow than mali gpu

Hello! Currently I am trying to inference VGG-16 through arm cpu. import tvm import tvm.relay as relay from tvm.contrib import graph_runtime import numpy as np import topi from tvm.relay.testing.temp_op_attr import TempOpAttr target_arm_cpu = tvm.target.create('llvm

[TVM Discuss] [Questions] [Auto TVM][CUDA] tune_graph is possible in cuda?

In Auto-tuning, graph_tuner is only doing in x86. Is there any way to do graph_tuner in cuda? --- [Visit Topic](https://discuss.tvm.ai/t/auto-tvm-cuda-tune-graph-is-possible-in-cuda/6219/1) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from thes

[TVM Discuss] [Questions] [ERROR] dmlc error occurred when compiling a model for mali gpu

Hello! I use rk3399 firefly board with LLVM 8.0.0 and ubuntu 18.04. I ran vgg16 on the board using the following code. import tvm from tvm import te import tvm.relay as relay from tvm.contrib import graph_runtime import numpy as np import topi from tvm.relay import t