for example, a graph include conv + bn + relu, can we run conv + bn on gpu and
relu on cpu?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/can-we-deploy-different-ops-in-a-graph-on-different-backends/11718/1)
to respond.
You are receiving this because you enabled mailing list mode.
Hi @Doofenshmirtz97,
Can you try modifying your PYTHONPATH assignment not to use the shell expansion
with `~` such as, I believe:
`PYTHONPATH=$PYTHONPATH:/home/tvm/python`
Optionally you could also try using tlcpack (https://tlcpack.ai) and a regular
virtualenv.
Hope that helps.
---
[Vi
[quote="sho, post:6, topic:11682"]
If you specify like below,
> ```
> TARGET = tvm.target.target.micro("stm32f746xx")
BOARD = "nucleo_f746zg" # or "stm32f746g_disco#"
> ```
Does it always mean you generate C?
[/quote]
Yeah--this is just a shortcut:
https://github.com/apache/tvm/blob/main/pyth
@sho no problem, apologies if this is a bit confusing.
[quote="sho, post:5, topic:11682"]
As you probably know, I was confused about LLVM, and how it is used. So LLVM is
used to build TVM compiler. LLVM also works when you input your model into TVM
compiler and get TVM’s IR. LLVM compiles the
Also, when I see the micro TVM tutorial,
https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_tflite.html#microtvm-with-tflite
I found that it specifies more concrete strings as the target.
If you specify like below,
> TARG
Hi @areusch,
Sorry for my late reply. I needed some time to clean up my thought.
Could you correct me if I'm wrong?
As you probably know, I was confused about LLVM, and how it is used.
So LLVM is used to build TVM compiler. LLVM also works when you input your
model into TVM compiler and get T
I followed the tutorial mentioned on the website for "Build TVM Runtime on
Device" on RaspberryPi
I added the line export PYTHONPATH=$PYTHONPATH:~/tvm/python to my ~/.bashrc
file. I am still receiving the error when I run this command:
> python -m tvm.exec.rpc_server --host 0.0.0.0 --port=909
@kevinthesun Is relay vm supported with Vitis AI workflow? if not is there any
success rate for compiling maskrcnn model for xilinx hw?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/supporting-faster-rcnn-and-mask-rcnn-models/2064/39)
to respond.
You are receiving this because you e
