areusch opened a new pull request #6948: URL: https://github.com/apache/incubator-tvm/pull/6948
The µTVM runtime has previously been fixed to use the builtin memory allocator. To avoid code duplication if an internal malloc is already linked, and as we look to a future where memory may need to be allocated in specific locations to support heterogenous execution, this PR allows each project to implement `TVMPlatformMemoryAllocate` and `TVMPlatformMemoryFree` to specify how to allocate tensor memory. Additionally, it makes the existing allocator available as a library. ---------------------------------------------------------------- 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: us...@infra.apache.org
