Thank you @masahi for helping edit the description for Vulkan! It looks pretty
nice to me :-)
Thanks @jiangjiajun for proofreading the PaddlePaddle-related text. Yep these
commits were not there a month ago when we collected the initial changelog
draft. Thanks to @vinx13, who acted swiftly and
Thanks @junrushao1994 !
There are 2 part I think we may need to fix
For the **Accepted RFCs** part,
> `[RFC-0019] Add paddlePaddle frontend`
it should be `[RFC-0019] Add PaddlePaddle frontend`, just a case problem
And for the **Frontends** part,
> **PaddlePaddle initial support #8645**
I ha
Should we wait for PyTorch TVM PR https://github.com/apache/tvm/pull/8777? It
should be merged soon.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/9416#issuecomment-957030631
Ok replaced with "Improved Vulkan backend" at the overview, and added unusually
more details in "Codegen Backends and Runtime" to show off our vk capability.
A critical bug fix in SPIRV codegen allows the Vulkan backend to produce
correct outputs on more hardwares and drivers. Added support for
[quote="manupa-arm, post:6, topic:11362"]
In the partition_for_* function where the full IRModule is visible (along with
@main and external functions) you could actually mutate the constants within
external function and hoist them out of the external function prior to calling
the relay.build(…
@masahi @Lunderberg Yeah I totally agree! Would you guys suggest more details
like "improved vulkan backends on ..."? Thanks a lot!
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/9416#i
@masahi
There is another option you could take here.
The wildcard() actually works here because the constant remains in @main
function of the IRModule.
In the partition_for_* function where the full IRModule is visible (along with
@main and external functions) you could actually mutate the c
Yeah I can see the difficulty you mentioned, and it might be possible that nvcc
is not available in runtime if the model is deployed to an edge device.
A combined approach would be leveraging the third BYOC option: custom
codegen/runtime. Specifically, we still generate the C/CUDA kernel and c
Better to replace "Vulkan backend" at the "major exciting experimental
features" section with `Improved Vulkan backend", since the vk backend has been
around for a long time by now.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on G
[quote="comaniac, post:3, topic:11362"]
This mechanism is used for the case that a BYOC backend attempts to manage the
constant values with certain processes, such as layout transform
[/quote]
CUTLASS does seem to support specialized layouts for gemm / conv2d. If we want
to make use of them an
> I'd suggest adding the BufferTransform data structure here which will be very
> helpful to other audience.
Sounds good, and I've added a description of it, and a possible data structure
for it.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly
Also, if there is any bug/issue blocking the release, please don't hesitate to
let us know in this thread :-)
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/8976#issuecomment-956449578
Hi all, we cut a v0.8 release branch for Apache TVM:
https://github.com/apache/tvm/tree/v0.8. Please find:
- The release note (candidate): https://github.com/apache/tvm/issues/9416
- The full changelog (candidate):
https://gist.github.com/junrushao1994/c669905dbc41edc2e691316df49d8562
There have
# Apache TVM v0.8 Release Note
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/9416
cc @junrushao1994 @zxybazh @comaniac
---
[Visit
Topic](https://discuss.tvm.apache.org/t/pre-rfc-compilation-configuration-representation/11372/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.
@Mousius Thanks for asking!
> does this mean that 0.8 will go out with half finished implementations for
> things, such as library integrations (i.e. CMSIS-NN) and tvmc arguments (tvmc
> is not yet stable as there's breaking changes incoming)
Yes, we directly cut main into the v0.8 branch:
htt
Your solution makes sense to me. This mechanism is used for the case that a
BYOC backend attempts to manage the constant values with certain processes,
such as layout transform. It works well for other codegens (e.g., JSON), but as
you pointed out, we never really solve this problem for C code
Inspired by the work of @mbs-octoml, I give you a new RFC for CompilationConfig!
# Summary
[summary]: #summary
This RFC supersedes [Migrating IRModules to
Attributes](https://github.com/apache/tvm-rfcs/blob/main/rfcs/0029-migrating-to-irmodule-attributes.md)
by replacing the various attribute
18 matches
Mail list logo
