Dear All,
I am wondering current progress of this item? Can I partition the graph and
run the in different devices with TVM?
---
[Visit
Topic](https://discuss.tvm.ai/t/graph-partitioning-and-heterogeneous-execution/504/31)
to respond.
You are receiving this because you enabled mailing
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.t
This is a proposal to do a minor (bugfix) release of v0.6, aka v0.6.1. Commits
will be cherry-picked to v0.6.1 branch. We follow the standard [Apache release
process](https://tvm.apache.org/docs/contribute/release_process.html)
I will go through the commits history to get a list of bug fixing
@manupa-arm that's the ultimate goal to solve 2 problems currently the merge
composite pass facing:
1. As you pointed out, the current approach to specify the composite pattern
requires users to make lots of similar patterns. This problem was reported by
@masahi and @jonso if I remember corre
@comaniac, I believe when you are saying you are going to re-write the
merge-composite with the pattern language that means you are essentially going
to replace the pattern tables with patterns from the language (as long as the
interface is concerned). Correct ?
I also dont see any problems
@comaniac Regarding composite vs. single operators, we actually have more
single ops than patterns. The composite functions appear more frequently though
pretty much entirely because of qnn.conv2d.
>From our perspective, composite pattern matching and merging annotation
>regions are no more o
I figured that was the reason you asked. I looked at the pattern language when
it is was first announced and did not see anything particularly worrying at the
time. We use merged-composite in a few places so I'll look at it again in the
next days to see if there are any issues we can anticipat
