+1
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/16368#issuecomment-1882127374
You are receiving this because you are subscribed to this thread.
Message ID:
+1
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/15521#issuecomment-1674113751
You are receiving this because you are subscribed to this thread.
Message ID:
Thanks @YuchenJin for updating this RFC!
>From the use-cases that I have observed in my experience, the symbolic shape
>capabilities allows TVM to handle dynamic workloads that cannot be handled in
>other frameworks and get more widely adopted. And we can quickly enable
>iterations of unity co
+1 (binding)
--
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/12651#issuecomment-1235948052
You are receiving this because you commented.
Message ID:
+1
On Tue, Aug 30, 2022 at 08:05 Yuchen Jin
wrote:
> +1
>
> --
> Reply to this email directly or view it on GitHub:
> https://github.com/apache/tvm/issues/12651#issuecomment-1231796765
> You are receiving this because you are subscribed to this thread.
>
> Message ID:
Please join us to welcome @denise-k as a new reviewer to TVM.
Denise is the main (co)authors of roadmap RFC and roadmap process:
- https://github.com/orgs/apache/projects/31
- https://github.com/apache/tvm-rfcs/pull/50
- https://discuss.tvm.apache.org/t/pre-rfc-tvm-roadmap/11171
And she helps t
I agree that the existing approach does not work well and support this RFC :+1:
---
[Visit Topic](https://discuss.tvm.apache.org/t/rfc-remove-codeowners/12095/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https
Sounds like a good case for https://github.com/tlc-pack/relax/issues/46
---
[Visit
Topic](https://discuss.tvm.apache.org/t/tvm-integration-with-external-dsp-accelerator-api/11641/3)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails
+1
--
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/9504#issuecomment-968362424
+1
- Ziheng
On Fri, May 14, 2021 at 01:50 Yuchen Jin
wrote:
> +1
>
> --
> You are receiving this because you commented.
> Reply to this email directly or view it on GitHub:
> https://github.com/apache/tvm/issues/7991#issuecomment-840724342
I vote for A0 for consistency with DLDataType / tvm::DataType
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-rename-tvmcontext-to-tvmdevice/9090/23)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://d
Great suggestion!
Can we make it as a nightly/weekly regression test utils and also consider
adding accuracy evaluation for quantization model into this loop?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-building-a-new-reproducible-benchmark-for-tvm/8496/2)
to respond.
You are
(
https://lists.apache.org/list.html?dev@tvm.apache.org)
- TVM website (https://tvm.apache.org/)
- Github issues (https://github.com/apache/incubator-tvm/issues)
Best regards,
Apache TVM (incubating) Team
--
Ziheng
Closed #6622.
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6622#event-3847455220
Thanks everyone for voting. The voting result has been sent out.
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6622#issuecomment-704531346
Dear TVM community,
I'm glad to announce the results of the vote.
This vote passes with 9 +1 votes (7 binding), no 0 votes, and 0 -1 vote.
+1 votes
* Yizhi Liu (binding)
* Tianqi Chen (binding)
* Byung-Gon Chun (binding)
* Zhao Wu
* Zhi Chen (binding)
* Thierry Moreau (binding)
* Jared Roesch
Dear TVM community,
This is a call for vote to release Apache TVM (incubating) version 0.7.0. This
is a major release with many new features and improvement. All users of Apache
TVM (incubating) 0.6 are advised to upgrade. The release is co-managed by Zhi
Chen (@zhiics).
Link to release notes
# Introduction
v0.7 is brings many major features. The community works together to refactor
the internal code base to bring an unified IR code structure with unified
IRModule, type system and pass infrastructure. We have also bought many
exciting new features, some highlights include:
* Initial
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the pull request is submitted, please request code reviews from
[Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers)
b
cc: @tqchen @yzhliu @zhiics
You can view, comment on, or merge this pull request online at:
https://github.com/apache/incubator-tvm/pull/6613
-- Commit Summary --
* [RELEASE] Update NEWS.md for v0.7
-- File Changes --
M NEWS.md (1338)
-- Patch Links --
https://github.com/apache/incu
@leandron @comaniac @tqchen
We are still waiting CI for #6597 and #6578 . I have added them into the
release note and let's merge them tomorrow morning.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apa
## API Changes
### DataType to runtime
- Rationale: DataType is a runtime data structure
- PRs https://github.com/apache/incubator-tvm/pull/4560
- Rename all old reference of tvm::Type to DataType
- ExprNode.type -> ExprNode.dtype, Expr.type() -> Expr.dtype()
- Move type constructors as static fun
I will add an `API Changes` section before `Deprecation`.
--
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/incubator-tvm/issues/6486#issuecomment-701059777
Nice work @spectrometerHBH!
I would like to give it a try! One question, how can I build the `tir.function`
after I define it with the script? Is the path has been pushed on master branch
now?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-hybrid-script-support-for-tir/7516/21)
Merged #6582 into master.
--
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/incubator-tvm/pull/6582#event-3818072496
@comaniac Thanks for checking! I have added missing ones except those are not
merged yet.
--
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/incubator-tvm/issues/6421#issuecomment-699131319
Merged #6552 into master.
--
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/incubator-tvm/pull/6552#event-3806749717
@apache/tvm-committers @jroesch @u99127 @comaniac
We have a release note candidate here:
https://github.com/apache/incubator-tvm/issues/6486
Please comment it if you have anything want to be added into this release or
other opinion.
--
You are receiving this because you are subscribed to th
# Performance Improvements
- Int8 GEMM performance enhancement using Cublas
([#4550](https://github.com/apache/incubator-tvm/pull/4550))
- Speedup TSIM with multi-threading
([#4491](https://github.com/apache/incubator-tvm/pull/4491))
- [Runtime][Contrib] Support cudnn softmax (#5214)
- [cuDNN] A
# Bug Fixes
- Add bfloat16 typeflag support
([#4525](https://github.com/apache/incubator-tvm/pull/4525))
- MSVC / Windows fixes
([#4455](https://github.com/apache/incubator-tvm/pull/4455),
[#4569](https://github.com/apache/incubator-tvm/pull/4569))
- Fix Makefile for howto_deploy
([#4457](http
## Operator Coverage
- Allow empty tensor for reshape, tile and strided_slice
[#4618](https://github.com/apache/incubator-tvm/issues/4618)
- Fix meaning of conv2d_transpose output_padding parameter";
[#4708](https://github.com/apache/incubator-tvm/issues/4708)
- Remove cpp upsampling and resize
# Feature Improvement
## Accelerator and Microcontroller Support
- Cleanup legacy verilog code
([#4576](https://github.com/apache/incubator-tvm/pull/4576))
- uTVM support for ARM STM32F746XX boards
([#4274](https://github.com/apache/incubator-tvm/pull/4274))
- Add --runtime=c, remove micro_dev
# Feature Improvement
## Accelerator and Microcontroller Support
- Cleanup legacy verilog code
([#4576](https://github.com/apache/incubator-tvm/pull/4576))
- uTVM support for ARM STM32F746XX boards
([#4274](https://github.com/apache/incubator-tvm/pull/4274))
- Add --runtime=c, remove micro_dev
@tqchen
You can view, comment on, or merge this pull request online at:
https://github.com/apache/incubator-tvm/pull/6552
-- Commit Summary --
* [COMMUNITY] Add Ziheng's key for ASF release
-- File Changes --
M KEYS (58)
-- Patch Links --
https://github.com/apache/incubator-tvm/pull
Hi @mwillsey,
The decentralizing code generation sounds a good idea technically! We choose
Python mainly for user-friendly. I would also like to know @tqchen's opinion
here.
[quote="mwillsey, post:9, topic:7930"]
On the topic of checking the generated code in, I’m not sure why that is
necessa
Merged #6511 into master.
--
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/incubator-tvm/pull/6511#event-3781544780
Congrats!
--
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/incubator-tvm/pull/6511#issuecomment-694735886
@zhiics Yep, we have an option to turn off the default method generation and
allow user to fill their customized code snippets.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-tvm-object-schema-dsl/7930/8) to
respond.
You are receiving this because you enabled mailing list mode.
Hi @jcf94,
[quote="jcf94, post:5, topic:7930"]
IMHO, advanced users who may benefit from it are more likely to write their C++
code directly, while other users may not really have a requirement on this.
[/quote]
First, this is not only for C++ code generation. In the future, we will extend
it
Hi @comaniac,
[quote="comaniac, post:2, topic:7930"]
* Are the generated .h and .cc files supposed to be tracked in the repo, or
they are more like the build files?
[/quote]
They will be tracked in the repo. But user should write the tschema for objects
instead of writing the cpp files direct
## Introduction
[TVM Object
system]([https://tvm.apache.org/docs/dev/runtime.html#tvm-object-and-compiler-stack](https://tvm.apache.org/docs/dev/runtime.html#tvm-object-and-compiler-stack))
provides a convenient and decent way to share objects between backend (C++)
and frontend (Python/Java/R
I have opened a gist for monthly reports from last v0.6 release:
https://gist.github.com/ZihengJiang/6d3440ec22852dc9baae2e3f278ad8b4
We can start organizing the monthly reports to the release note template.
@zhiics @tqchen
--
You are receiving this because you are subscribed to this thread.
# New Features
## Accelerator
## Ansor
## Frontend and User Interface
## Relay
## Runtime
## TIR
## Quantization
# Feature Improvement
# Performance Improvements
# Documentation
# Build and Tests
# Bug Fixes
# Known Issues
# Deprecation
--
You are receiving this because you are subs
Please join us to welcome Hao Yu (@comaniac) as a new Committer. Hao has been
actively contributing to Relay, BYOC and Ansor. Hao is also quite active in
reviewing and providing suggestions to a lot of pull requests, RFCs as well as
answering questions in the forum.
- [Commits
History](https:/
Ack
- Ziheng
On Thu, Aug 27, 2020 at 17:18 Haichen Shen wrote:
> Ack
>
>
>
> On Thu, Aug 27, 2020 at 4:38 PM Thierry Moreau
>
> wrote:
>
>
>
> > Ack
>
> >
>
> >
>
> >
>
> > > On Aug 27, 2020, at 4:36 PM, YiZhi Liu wro
+1 (binding)
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/6332#issuecomment-679377654
+1
Looking forward to this!
--
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/incubator-tvm/issues/6299#issuecomment-675763639
+1
--
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/incubator-tvm/issues/5947#issuecomment-651301867
+1
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/5939#issuecomment-650471485
+1
--
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/incubator-tvm/issues/5102#issuecomment-601498167
Merged #4841 into master.
--
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/incubator-tvm/pull/4841#event-3019198359
Please join me to welcome @comaniac as a new reviewer. He has been working on
improving operators in topi and quite active in code review for the community.
- [Commits History](https://github.com/dmlc/tvm/commits?author=comaniac)
- [Code
Review](https://github.com/dmlc/tvm/pulls?utf8=%E2%9C%93&
# Learning-based Automated Quantization
## Background
One year before, I have implemented a quantization workflow in tvm:
[issue](https://github.com/apache/incubator-tvm/issues/2259),
[pull](https://github.com/apache/incubator-tvm/pull/2116). Brought the idea
from some existing quantization f
+1
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/4443#issuecomment-560223618
Welcome comment and discussion! @cylinbao @yuluny2 @tmoreau89 @Huyuwei @tqchen
--
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/incubator-tvm/issues/4332#issuecomment-553681206
A significant driver of progress in deep learning has been advances in
computational resources. While those resources are often limited, the is a
trend to replace dense computation in DNN with sparse computation for speeding
up / saving memory to enable larger models. For example: [neural netwo
@MarisaKirisame Checked. I listed it here just because that it did not go into
the last release cycle
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/2623#issuecomment-522143532
Please join us to welcome @hlu1 as a Committer of the TVM stack. His
contributions spans caffe2 frontends, NNPack integration and graph runtime, and
has been active in reviewing PRs.
- [Commit history](https://github.com/dmlc/tvm/commits?author=hlu1)
- [Code
reviews](https://github.com/dmlc/tv
# TVM Monthly - April 2019
https://discuss.tvm.ai/t/tvm-monthly-april-2019/2426
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/2623#issuecomment-47260
+1
--
You are receiving this because you commented.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/2973#issuecomment-480965723
60 matches
Mail list logo
