Considering the weight of every layer will be an individual input, it might be
fine.
Could you print out the graph after the partition pass? For example:
```
print(mod)
mod = relay.transform.AnnotateTarget("external_compiler")(mod)
mod = relay.transform.MergeCompilerRegions()(mod)
mod = relay.transform.PartitionGraph()(mod)
print(mod)
```
So that we can compare if the second printed module was correctly partitioned.
---
[Visit
Topic](https://discuss.tvm.ai/t/seeing-many-input-placeholders-in-graph-json-using-byoc/6708/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/4904aa757ef0f07720d764244780c3a2d5c511acef7b3dd996928de62dc72d6e).
