tqchen created an issue (apache/tvm#18255) We have been working on a series of refactor to bring tvm ffi into its own independent module. As of now, the ffi module is now a standalone module build from ground up, that takes minimal dependencies from the rest of the project. This is a formal vote to bring tvm ffi into its own module so it can evolve independently and benefit other ml system projects
NOTE: this thread is being mirrored in dev@ This vote will be open for at least one week, please vote: +1 = approve +0 = no opinion -1 = disapprove (provide reason) -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/18255 You are receiving this because you are subscribed to this thread. Message ID: <apache/tvm/issues/[email protected]>
