f2013519 opened a new pull request, #16915: URL: https://github.com/apache/tvm/pull/16915
### Background: This PR adds Marvell software runtime support as outlined in the pre-RFC here (refer to Phasing section, Phase 2): https://discuss.tvm.apache.org/t/prerfc-byoc-integrating-marvell-ml-ai-accelerator-to-the-tvm-byoc-framework/16155 Our initial PR added basic support for partitioning and compilation (https://github.com/apache/tvm/pull/16570). This follow up PR integrates **mrvl-tmlc** (Marvell's ML compiler which generates MLIP ISA) and **mrvl-mlsim** which is a software simulator tool to simulate the MLIP hardware. This toolchain is hosted at our MarvellMLTools GitHub repo: https://github.com/MarvellEmbeddedProcessors/MarvellMLTools ### Summary of Changes: The **mrvl-tmlc** compiler is invoked during compile time to generate MLIP instructions which are embedded in the runtime. The runtime then invokes the **mrvl-mlsim** tool to process the input, simulate the MLIP ISA instructions and return the output to the TVM runtime. -- 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: commits-unsubscr...@tvm.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org