[TVM Discuss] [Questions] How do you debug the C++ core while launching from Python?

I do this using CLion (which supports Python as well as C++). You can set up two different launch configurations for your program, one that launches it as a Python app and the other as a C++ app. Then if I need to debug the C++, I can launch it in debug using the C++ config and the graphical d

[TVM Discuss] [Questions] Same shape pattern

The sort of case I'm thinking of is when a mutation takes place, the mutated part of the graph won't have types associated with it (at least, not until type_infer is called on the expression again). It's not immediately obvious to me whether that's happening in this example. But now I've thoug

[TVM Discuss] [Questions] Same shape pattern

There is another way types can go awry in the dataflow matcher. When things get mutated they lose their type info until the rewrite is completed. We might want to start treating that behaviour as a bug because it's caught me out before. Maybe @mbrookhart can comment? --- [Visit Topic](htt

[TVM Discuss] [Questions] Same shape pattern

Have you tried using checked_type rather than _checked_type_? --- [Visit Topic](https://discuss.tvm.ai/t/same-shape-pattern/7012/5) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubsc

[TVM Discuss] [Questions] BYOC and the VTA missing link?

Just in terms of BYOC's capabilities, it's worth mentioning that one of the reasons all the codegens accept Relay rather than TIR is because BYOC is implemented in Relay. There's no infrastructure currently to partition TIR functions and I don't think it would be a simple extension (maybe the

[TVM Discuss] [Questions] [BYOC] Problem about subgraph with TupleTypeNode inputs

I have a candidate fix with this PR: https://github.com/apache/incubator-tvm/pull/5476 --- [Visit Topic](https://discuss.tvm.ai/t/byoc-problem-about-subgraph-with-tupletypenode-inputs/6522/6) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from t

[TVM Discuss] [Questions] [BYOC] Problem about subgraph with TupleTypeNode inputs

Hi, welcome to the forum :) I'm working on fixing this exact issue at the moment. It comes about because constant tuples are not correctly propagated into the partitioned regions so you can't see the data of the tuple, only its type. I hope to have a fix in review either later today or tomorro

[TVM Discuss] [Questions] Incorrect generated function after PartitionGraph pass

This should be resolved by this PR: https://github.com/apache/incubator-tvm/pull/5320 :) --- [Visit Topic](https://discuss.tvm.ai/t/incorrect-generated-function-after-partitiongraph-pass/6380/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe fro

[TVM Discuss] [Questions] [External CodeGen] Status of Annotating composite functions?

Status update! I've put on the following two PRs which hopefully will allow for composite function annotation: [5261](https://github.com/apache/incubator-tvm/pull/5261), [5262](https://github.com/apache/incubator-tvm/pull/5262). Feel free to take a look. --- [Visit Topic](https://discus

[TVM Discuss] [Questions] How can I transfer a list of functions?

I've found out I can do this by just passing each function as it's own argument and then collecting them together from TVMArgs. --- [Visit Topic](https://discuss.tvm.ai/t/how-can-i-transfer-a-list-of-functions/6239/2) to respond. You are receiving this because you enabled mailing list mo

[TVM Discuss] [Questions] How can I transfer a list of functions?

I'm trying to pass a list of functions from Python to C++. However, this doesn't seem possible at the moment because tvm::Array can only contain objects deriving from ObjectRef (which PackedFunc does not). Is there another approach I can take? In particular, it's important that the order of th

[TVM Discuss] [Questions] [External Codegen] Constant tensors in c-codegen

Ah, I understand now. We'll have a look at how viable that'll be for ACL. Thanks for the suggestion! --- [Visit Topic](https://discuss.tvm.ai/t/external-codegen-constant-tensors-in-c-codegen/5890/19) to respond. You are receiving this because you enabled mailing list mode. To unsubscrib

[TVM Discuss] [Questions] [External Codegen] Constant tensors in c-codegen

How are you compiling? We could serialize the graph, but we'd then need to codegen the relevant ACL API calls on the remote and compile it into something that can be executed. We can't do that without a toolchain though which can't be guaranteed. --- [Visit Topic](https://discuss.tvm.ai/

[TVM Discuss] [Questions] [External Codegen] Constant tensors in c-codegen

I've had a chance to look at this now and it seems like it's quite a fundamental issue with C codegen, not just ACL. This will make a lot of compile-time optimisations impossible as there's no reasonable way to handle large constant tensors in the codegen. This we be especially prevalent when

[TVM Discuss] [Questions] [External CodeGen] Status of Annotating composite functions?

AnnotateTarget doesn't support composite functions at the moment. I intend to send a PR to resolve this very soon (hopefully this week). You can use MergeCompilerRegions if you like, but this will only be applicable if you also support conv2d, bias and relu individually as well as merged.

[TVM Discuss] [Questions] [AutoTVM]How to continue interrupted auto-tuning?

I've been thinking about a more robust solution to this for a while and have some scripts that implement a sort of AutoTVM 'cache' that I use when autotuning. I'll try and turn these into a PR and open an RFC to see if anyone would be interested. --- [Visit Topic](http://tracking.discuss