[Setup RPC System — tvm 0.13.dev0 documentation
(apache.org)](https://tvm.apache.org/docs/dev/how_to/setup_rpc_system.html)
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rpc-related-whats-the-difference-between-rpc-proxy-rpc-server-rpc-tracker/3054/3)
to respond.
You are receiving t
Yes, this is the common issue that hardware vendor meet when integrating there
tool chain through BYOC.
You can refer the method used by tensorRT,
1. parttion any op your acc supported, then maybe you get multiple your acc
subgraph.
2. reinline the subgraphs that haven't big computation into
I haven't used `tvm::Dump(xxx)`, I use `call
(size_t)puts(PrettyPrint(xxx).c_str())` when the `xxx` is a large node, e.g.,
the whole of PrimFunc, you can try with these large node.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/finding-types-of-tvm-objects-and-accessing-their-attribut
I use the same way, and when I need inspect more details of the class object, I
will use `p PrettyPrint(xxx).c_str()`, in addition if I want a more clear
display(do the real line break instead of just print it as "\n"), the gdb
command `call (size_t)puts(PrettyPrint(xxx).c_str())` will be used
Yes, the relative import will make TVM distribute as a sub directory easy, but
as you said, it really is a heavy work, in addition the disadvantage of
relative(i.e., it is hard to find the real file location from the import
statement) maybe will hurt TVM code.
---
[Visit
Topic](https://d
Thanks for replying, but it maybe unacceptable for our customers to set a
specific value in PYTHONPATH after install our released python package.
The only method I can found to achieve the same goal is appending the path
`/nn_builder` to `sys.path` in file `/nn_builder/__init__.py`.
Do you
I have found below Relay IR when doing some job with ResNet-50, we can see the
2 add operators are can be merged to 1 add, the below log is build with
opt_level=3.
```
%21 = nn.conv2d(%20, meta[relay.Constant][2] /* ty=Tensor[(32, 8, 1, 1, 8,
8), int8] */, padding=[0, 0, 0, 0], channels=256,
>From browsing the source code, I found that the doxygen documents are
>controled by "docs/Doxyfile", from the configuration file, why only the
>"include/tvm" is set to "INPUT"?
It seems that we only decide to generate the doxygen documents for header files
now, is there some reason for that?
>From the official document web page
>[https://tvm.apache.org/docs/api/links.html](https://tvm.apache.org/docs/api/links.html),
> we can find the [C++ doyxgen
>API](https://tvm.apache.org/docs/api/doxygen/index.html), but in the doyxgen
>web page there isn't any classes of namespace "tvm::code
