Archermmt commented on issue #15233: URL: https://github.com/apache/tvm/issues/15233#issuecomment-1760886553
@Lunderberg sorry for the late reply.... I've checkout the failures, which is cause by from_fx function of relax. The failures of test_translate_relax.py and test_translate_torch.py have the same reason. I think MSC is not the source of the failures, it just build new modules based on relax and relay, without touching the basic codes of them. And the reasons way build a duplicate "relay -> relax" method: 1. A operator-level conversion is needed, as you said. This is essential when developers want to use relay based features (like me, testing tensorflow). 2. Using relay also have some problems in optimizing the model, especially in quantization, pruning, parameter reusing and training. The real process is relay -> MSCGraph -> relax, MSCGraph is the key DAG structure in model compression. This via_relax=False only shows an example of using MSC with relax and relay, not meaning to be a converted between relay and relax. When the final solution for the "operator-level conversion from relay to relax" is done, I will change the relay-relax method accordingly. Thanks for watching ! -- 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]
