-
Notifications
You must be signed in to change notification settings - Fork 3.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[BUG] rpc.connect error #2475
Comments
Can you share some more details of your network setup? Is it IPv6 or IPv4? We will need to add a regression test for this. |
[Evnvironment] tx1 <------- WI-FI ------> Router <------- WI-FI ------> MacOS Nvidia tx1 IP: 10.100.31.193 [Operation]
tx1 is reachable and it is listening 9090:
If this bug cannot reappear stably, please tell me the log you need. |
Great, thanks. I have a macOS machine and will try to reproduce this tomorrow. |
I have reproduced the bug, it seems to be related to the wrong size being passed into |
Also, feel free to submit a PR for the spelling fix. |
By the way, what is the meaning of "PR" ? |
(pull request) |
[Description]
According to Deploy the Pretrained Model on Raspberry Pi,
I have compiled the project with llvm-4.0, but
deploy_model_on_rasp.py
crashed ontvm/src/runtime/rpc/rpc_socket_impl.cc:47
:It seems like some network error caused assertion, then I checked the commit log and revert it to
e4b9f986dab8c48ba109a52106565fc4be6b67c4
, recompile the project, it works well !Please check the commit
0806b69e3fb136226fa1dafad00bd2c606cc998d
carefully, here be dragons.[Environment]
I compile tvm on macOS Mojave 10.14.2, deploy
net.tar
to Nvidia tx1.[Document]
There is a spell error in Deploy the Pretrained Model on Raspberry Pi
device
notdevcie
The text was updated successfully, but these errors were encountered: