You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "f2013519 (via GitHub)" <gi...@apache.org> on 2024/02/14 07:51:37 UTC
[PR] [Marvell BYOC]: Marvell AI Accelerator Integration - Phase 1 [tvm]
f2013519 opened a new pull request, #16570:
URL: https://github.com/apache/tvm/pull/16570
### Summary
This PR adds support for partitioning and compiling the Marvell BYOC target along with initial integration with tvmc. Support for the runtime (simulator based & hardware) and other features (int8) will be added in phases as described in the pre-RFC post: https://discuss.tvm.apache.org/t/prerfc-byoc-integrating-marvell-ml-ai-accelerator-to-the-tvm-byoc-framework/16155.
**Please see the pre-RFC for a detailed description of the design and roadmap going forward.**
### Building
We have introduced a new cmake flag:
**USE_MRVL=ON/OFF**
This flag enables Marvell BYOC codegen and is required for using the Marvell BYOC functionality, running unit tests, etc.
### Usage
The tvmc interface for Marvell BYOC will be similar to other composite targets.
The below command is an example of cross-compilation of an ONNX model for an Octeon target.
python3 -m tvm.driver.tvmc compile
--target="mrvl, llvm" \
--target-llvm-mtriple=aarch64-linux-gnu \
--target-llvm-mcpu=neoverse-n2 \
--target-mrvl-num_tiles=4 \
--cross-compiler aarch64-linux-gnu-gcc \
--output model.tar \
model.onnx
Supported operators will be partitioned and compiled for the MLIP and the remaining operators will be compiled for the ARM Neoverse cores using the default LLVM target.
TVM Python API based compilation is also supported, please refer to the doc added as part of this PR for details.
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Marvell BYOC]: Marvell AI Accelerator Integration - Phase 1 [tvm]
Posted by "Hzfengsy (via GitHub)" <gi...@apache.org>.
Hzfengsy merged PR #16570:
URL: https://github.com/apache/tvm/pull/16570
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Marvell BYOC]: Marvell AI Accelerator Integration - Phase 1 [tvm]
Posted by "f2013519 (via GitHub)" <gi...@apache.org>.
f2013519 commented on PR #16570:
URL: https://github.com/apache/tvm/pull/16570#issuecomment-1947820702
> LGTM. BTW, as we are moving to TVM Unity / Relax, would be great if you could consider supporting MRVL for unity flow for emerging needs (e.g. LLMs)
Thanks @Hzfengsy. We are closely following TVM Unity / Relax development and it is part of our future roadmap. We will work on it once we complete the initial Relay flow support.
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [PR] [Marvell BYOC]: Marvell AI Accelerator Integration - Phase 1 [tvm]
Posted by "f2013519 (via GitHub)" <gi...@apache.org>.
f2013519 commented on PR #16570:
URL: https://github.com/apache/tvm/pull/16570#issuecomment-1947153288
cc @Hzfengsy @vinx13
--
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-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org