leandron commented on a change in pull request #7577:
URL: https://github.com/apache/tvm/pull/7577#discussion_r589318762
##########
File path: docs/deploy/vitis_ai.rst
##########
@@ -459,21 +459,21 @@ target and partition the graph.
.. code:: python
- target='DPUCADX8G'
- mod = partition_for_vitis_ai(mod, params, target)
+ dpu = 'DPUCADX8G'
+ mod = partition_for_vitis_ai(mod, params, dpu)
Now, we can build the TVM runtime library for executing the model. The
TVM target is 'llvm' as the operations that can't be handled by the DPU
-are executed on the CPU. The Vitis-AI target is DPUCADX8G as we are
-targeting the cloud DPU and this target is passed as a config to the TVM
+are executed on the CPU. The Vitis-AI DPU is DPUCADX8G as we are
+targeting the cloud DPU and this DPU indetifier is passed as a config to the
TVM
Review comment:
```suggestion
targeting the cloud DPU and this DPU identifier is passed as a config to the
TVM
```
##########
File path: python/tvm/driver/tvmc/composite_target.py
##########
@@ -22,7 +22,7 @@
from tvm.relay.op.contrib.arm_compute_lib import partition_for_arm_compute_lib
from tvm.relay.op.contrib.ethosn import partition_for_ethosn
from tvm.relay.op.contrib.vitis_ai import partition_for_vitis_ai
-from tvm.contrib.target import vitis_ai
+from tvm.contrib.target import vitis_ai # pylint: disable=unused-import
Review comment:
Out of curiosity: why do we need this import here? is this for some
module initialisation purposes?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
