tvm-rfcs
tvm-rfcs copied to clipboard
apache
A home for the final text of all TVM RFCs.
Hi community: Follow the guide in the README.md, this PR is summited for the forum topic: https://discuss.tvm.apache.org/t/tvm-explorer-infrastructure/13457 Thank you!
This RFC summarizes an overall technical strategy on establish TVM Unity connection milestone. It is supplementary to the technical RFCs about specific components. [rendered](https://github.com/tqchen/tvm-rfcs/blob/main/rfcs/0091-establish-tvm-unity-connection.md) [discuss thread](https://discuss.tvm.apache.org/t/establish-tvm-unity-connection-a-technical-strategy/13344)
This RFC proposes to upstream the core foundation of Relax including its IR, compilation flow, and runtime, to address the critical needs identified by the TVM community, and enable a...
Introducing the addition of Arm Architecture's Scalable Vector Extension (SVE) in TVM containing initial VLA and predication implementation, based on earlier work by Giuseppe Rossini. @mbaret
This commit introduces the notion of constant memory pools and removes the need to define access on each of the targets.
This RFC proposes a new format to keep our Docker images used in CI, moving away from our current incremental numbering to a more meaningful format that contains a timestamp...
Prompted by https://github.com/apache/tvm/pull/10474, this RFC proposes removing tophub from the default compilation workflow. If you rely on tophub being the implicit default, please comment on this RFC. @masahi @comaniac
This is an RFC PR for [apache/tvm#10650](https://github.com/apache/tvm/pull/10650). cc @FrozenGene @masahi @comaniac
* Integrate Marvell’s ML/AI accelerator with TVM BYOC framework in order to bring the TVM ecosystem to Marvell customers. We have also posted a pre-RFC at https://discuss.tvm.apache.org/t/pre-rfc-byoc-marvell-ml-ai-accelerator-integration/11691. Plus, we have...
