Thanks for the prompt response.
[quote="comaniac, post:2, topic:9808"] On the other hand, if you meant to generate an executable module without TVM runtime, this is a part of the AOT (ahread of time) compilation which hasn’t been fully supported yet. [/quote] Indeed, I was looking for AOT compilation and not JIT. I understand that parts of the code which are annotated by a "target" are marked, followed by merging compiler regions and generating the code partitioned between the target and TVM. For the parts annotated by "target", is it possible to write custom passes, which are target dependent before relay.build is called? I am trying to achieve the following: 1. for the compiler regions annotated for the target, decompose or merge them them into custom nodes (which are specific to the target) 2. Run optimization passes on these nodes (targeted towards different goals --- say low energy or high throughput) depending on the target constraints 3. Invoke the code gen for this part. Ideally, all the operators would be offloaded to the accelerator and hence I do not plan to use the TVM runtime. Would you recommend doing this with relay transform passes or to write custom passes outside TVM with the generated json structure? It would be convenient to use the relay pass infrastructure. --- [Visit Topic](https://discuss.tvm.apache.org/t/byoc-json-codegen-for-byoc/9808/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/4166c184ab2d44c9d119a7a5f4f6f23f110970e314ad53e09ce09caafa2611e5).
