yongwww commented on PR #16531: URL: https://github.com/apache/tvm/pull/16531#issuecomment-1975676660
@chunit-quic thanks for the reply! I'm new to the Torch ExportedProgram, I noticed that the export API is still under development (https://github.com/pytorch/executorch/issues). If `ExportedProgram` is the preferred way to obtain the GraphModule compared to `fx.symbolic_trace`, we could consider utilizing the export API to get the `ExportedProgram` and updating the fx translator to work with the `GraphModule` in the `ExportedProgram`. For insights into SLM, please refer to this [[documentation](https://discuss.tvm.apache.org/t/design-torchy-productive-model-definition-in-tvm-unity/15404)](https://discuss.tvm.apache.org/t/design-torchy-productive-model-definition-in-tvm-unity/15404) and explore the code in `relax/frontend/nn`. If, after further evaluation, SLM aligns with your requirements, we could consider shifting our focus directly to it. cc: @MasterJH5574 @junrushao @LeshengJin @cyx-6 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
