Hello, is your problem solved now? I also encountered a similar problem.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/adding-manual-scratchpad-management-code-in-custom-tir-pass/8614/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from th
This is the relationship and the source of the data：
In the picture, the top is what I have and the bottom is what I want.
Among them：
x == A,y == B,z == C;
GM2LM is data loading
LM2GM is data write back
How can I add something to TIR to
Maybe the slowdown is due to int16 fallback? Or, since you modified the
compute, the "right" schedule may not be getting called.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/intution-on-why-this-int8-algorithm-is-slower/12920/2)
to respond.
You are receiving this because you enable
I've been exploring quantization in TVM, and one thing that I found that on the
CPU there is a special compute/schedule for running int8 conv2d on the CPU
([see
here](https://github.com/apache/tvm/blob/main/python/tvm/topi/x86/conv2d_int8.py#L132)).
From what I can tell, it seems to be pret
Hello, I have a very similar problem
I was trying to implement deeplabv3plus
using this code -
https://github.com/keras-team/keras-io/blob/master/examples/vision/deeplabv3_plus.py
The model compiles in tensorflow, also able to convert to onnx
but finally when I run this function
mod, params =
