kazum opened a new pull request #5283: [RUNTIME][CONTRIB] CoreML Runtime URL: https://github.com/apache/incubator-tvm/pull/5283 This PR introduces a runtime to load and execute CoreML models from TVM. To run CoreML inference via RPC, please setup [iOS TVM RPC](https://github.com/apache/incubator-tvm/tree/master/apps/ios_rpc) beforehand. This is useful for a baseline benchmark measurement. In addition, we could extract a subgraph and offload it to CoreML with this runtime - it would be important for optimization on iOS since using CoreML is the only way to leverage Apple's Neural Engine. @tqchen @ZihengJiang @FrozenGene Could you help to review this?
---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
