Hello,
I had similar problem, for me, when I read following error, that means that
some instruction should return some values, but unexpectedly it was
killed/shuted down. In my case it was timeout lower than expected runing time.
You should monitor what is going on on another side of RPC, i.e
Hello,
I'm testing tvm on android phone via RPC. I'm wondering how to know which flags
I have to use, e.g.
I have phone with mt6762v platform, which has cortex A53 procesor and PowerVR
GPU. Android is aarch64, so I decided to you following flags: `llvm
-mtriple=aarch64-linux-gnu -device=arm_
I think I have solved my problem, and I think it was a networking problem
---
[Visit
Topic](https://discuss.tvm.apache.org/t/have-anyone-deployed-rpc-tracker-to-k8s-cluster/12242/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails
I have deployed rpc tracker to k8s cluster, at the begining it looks like it
was working:
- devices can connect to rpc tracker
- query rpc tracker results with free devices
- rpc is behind k8s' service and is configured in deployment with one Pod
But when I do simple benchmark run, i'm getting
Hello,
In ubuntu I can see a lot of compilers for aarch64 or arm32 architecture, e.g.:
```
apt-cache search aarch64-linux
gobjc++-11-aarch64-linux-gnu - GNU Objective-C++ compiler
gobjc++-9-aarch64-linux-gnu - GNU Objective-C++ compiler
gobjc++-aarch64-linux-gnu - GNU Objective-C++ compiler for
Hello,
I have trouble with runing autotuning using OpenCL and RPC. When I call tvmc
tune command with `--help` command I'm getting a lot of options, e.g.:
```
target opencl:
--target-opencl-max_num_threads TARGET_OPENCL_MAX_NUM_THREADS
target opencl max_num_threads
-
Hello,
In TVM4J subproject there are folders linux-x86_64 and osx_x86_64 but there is
no assembly folders for arm32, aarch64, windows folders?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/why-in-tvm4j-there-is-not-arm-folders/11482/1)
to respond.
You are receiving this because you
During model compilation I'm getting some warning messages, and at the end I
see this message. Using `-v` flag doesn't change anything.
```
One or more operators have not been tuned. Please tune your model for better
performance. Use DEBUG logging level to see more details.
```
---
[Visit
