**Option C0:**
The original intention was to use Relay to ONNX as serialization format only. **Option C1:** It seems interesting and can fit naturally in TVM. But wanted to discuss a few of the points below. First, let me put down the different properties or attributes of a target in general. * Ability to annotate Relay graph for specific op support * Ability of Relay Lowering which is Codegen * Runtime Module When we treat ONNX as a target, we will be able to annotate the graph for specific ops support. Also, we will be able to lower Relay to ONNX. But since ONNX is an IR, there are multiple runtimes such as onnxruntime, TensorRT etc which support it. So there can be multiple runtime modules. We will have to think about how we are going to support these runtimes. The options I can see are. * R0: Implement a generic ONNX runtime and allow vendors to extend it for their specific runtime. * R1: Add composite Targets like “ONNX-TensorRT”., “ONNX-ONNXRuntime”. **Let me know your thought around it.** **I would love to hear other's opinions as well regarding C0, C1 and R0, R1.** @smallcosca, Thanks for sharing the link for your work on Relay to ONNX. It's great work and will definitely help. I also have a PR against Apache TVM repo. I will refer to your implementation and so that we can take the best of both the worlds. --- [Visit Topic](https://discuss.tvm.ai/t/rfc-relay-to-onnx/6101/10) 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/f39ccceb843aba5a2c785b13077c767685379e09df09b3f9577bd8c141d48455).
