ymwangg commented on issue #8378:
URL: https://github.com/apache/tvm/issues/8378#issuecomment-871809927
The document may be misleading. You need to compile the relay expression.
The following code should work.
```python
import tvm
from tvm import relay
from tvm.relay import create_executor
x = relay.var("x", shape=[3],dtype="int32")
y = relay.var("y", shape=[2],dtype="int32")
out = relay.meshgrid([x, y]).astuple()
f = relay.Function([x,y], out)
mod = tvm.IRModule.from_expr(f)
executor = create_executor(kind="graph", mod=mod, target="llvm")
res = executor.evaluate()(np.array([1,2,3]).astype("int32"),
np.array([4,5]).astype("int32"))
print(res)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
