Re: [apache/tvm] [VOTE] Release Apache TVM v0.20.0.rc0 (Issue #17861)

Hzfengsy left a comment (apache/tvm#17861) +1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/17861#issuecomment-2820689416 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.19.0.rc0 (Issue #17602)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/17602#issuecomment-2613009112 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release][Dont Squash] Update version to 0.19.0 and 0.20.0.dev on main branch (PR #17586)

@tqchen @yongwww are updating CI machines. would be great if you guys could help fix it :) -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/17586#issuecomment-2586046975 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release][Dont Squash] Update version to 0.19.0 and 0.20.0.dev on main branch (PR #17586)

@tvm-bot rerun -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/17586#issuecomment-2585119636 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.18.0.rc0 (Issue #17471)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/17471#issuecomment-2430514978 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release][Dont Squash] Update version to 0.18.0 and 0.19.0.dev on main branch (PR #17461)

Merged #17461 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/17461#event-14615840054 You are receiving this because you are subscribed to this thread. Message ID:

[Apache TVM Discuss] [Development] Phasing out Legacy Components

LLMs are fundamentally transforming the paradigm of ML deployment and compilation. Simultaneously, the increasing complexity of ML optimization pipelines has rendered many legacy components inadequate for meeting rapidly evolving requirements. On the other hand, the open-source community face

Re: [apache/tvm] [Misc] Add script for testing release package (PR #16956)

Merged #16956 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/16956#event-12652476117 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.16.0.rc0 (Issue #16912)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/16912#issuecomment-2080402374 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.15.0.rc0 (Issue #16428)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/16428#issuecomment-1911507621 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [cherry-pick][COMMUNITY] Add new key for release signing (#16419) (PR #16424)

Merged #16424 into v0.15.0. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/16424#event-11522414083 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Transition Main to Unity (Issue #16368)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/16368#issuecomment-1882124000 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC][SYCL] add sycl backend RFC (PR #105)

@tqchen @masahi Please take a look if you are interested. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/105#issuecomment-1784540899 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.14.0.rc0 (Issue #15974)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/15974#issuecomment-1782380337 You are receiving this because you are subscribed to this thread. Message ID:

[apache/tvm] Pre-release v0.14.0.rc0 - Apache TVM v0.14.0 rc0

# Introduction The TVM community has worked since the v0.13.0 release to deliver the following new exciting improvements! The main tags are below (**bold text is with lots of progress**): - Community, RFC - **Arith**, MetaSchedule - Adreno, ArmComputeLibrary, Hexagon, Metal, OpenCL & CLML, ROCm

Re: [apache/tvm] [Release] [Dont Squash] Modify version number to 0.14.0 and 0.15.0.dev on main branch (PR #15934)

Merged #15934 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/15934#event-10664637526 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release] Update version to 0.14.0 on main branch (PR #15847)

In the previous practice, we didn't change tags into the release version on the main branch. Pros: It will make the release branch a commit on the main branch, rather than diverging from the commit line Cons: There might be commits after v0.14 but before we change it to v0.15dev Happy to hear

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

I withdraw this proposal in favor of the simpler and better process in #102 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/95#issuecomment-1693505583 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

Closed #95. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/95#event-10194035435 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [Process RFC] Clarify Community Strategy Decision Process (PR #102)

Merged #102 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/102#event-10194018705 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC] Introduce TPAT (TVM Plugin Autogen Tool) (PR #103)

Can you please review this? @buptqq -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/103#issuecomment-1681553503 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Clarify Community Strategy Decision Process (Issue #15521)

+1. After reviewing all the comments from the related threads and wearing the community hat, I think this is the proper process -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/15521#issuecomment-1673414738 You are receiving this because you are subscrib

Re: [apache/tvm-rfcs] [Process RFC] Clarify Community Strategy Decision Process (PR #102)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/102#issuecomment-1666500814 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [Release] v0.13.0 release schedule (Issue #15134)

I have Updated Github pre_release to release and also upload to the svn release folder -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/15134#issuecomment-1651578205 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.13.0.rc0 (Issue #15313)

+1 (binding) -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/15313#issuecomment-1635263420 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [Release] v0.13.0 release schedule (Issue #15134)

@ysh329 packages are ready now. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/15134#issuecomment-1635183506 You are receiving this because you are subscribed to this thread. Message ID:

[apache/tvm] Pre-release v0.13.0 - Apache TVM v0.13.0

# Introduction The TVM community has worked since the v0.12.0 release to deliver the following new exciting improvements! The main tags are below (**bold text is with lots of progress**): - Community, RFC; - Frontend: TensorFlow/TFLite, Pytorch/Torch, Paddle, keras; - Runtime: Adreno, OpenCL &

Re: [apache/tvm] [release] Bump version numbers to 0.13.0 (PR #15216)

finished in #15273 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/15216#issuecomment-1628773856 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release] Bump version numbers to 0.13.0 (PR #15216)

Closed #15216. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/15216#event-9773585388 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [Release] Fix version number on branch v0.13.0 (PR #15273)

Merged #15273 into v0.13.0. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/15273#event-9773568538 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release] Bump version numbers to 0.13.0 (PR #15216)

cc @tqchen -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/15216#issuecomment-1623196204 You are receiving this because you are subscribed to this thread. Message ID:

[Apache TVM Discuss] [Meetup] Recap: Meetup in Beijing, gathering more than 140 attendees!

Thanks @antonia0912 for the comprehensive summary. Allow me to provide some additional insights: Based on the input received from participants and the local community, there are several shared areas of interest: 1. There is a growing interest in TVM Unity, particularly due to its adaptabilit

[Apache TVM Discuss] [Development/unity] [Discussion] A Technical Approach to LLMs with TVM Unity

Thanks TQ for the great question. We are working on dlight, a lightweight auto-scheduler for dynamic shape workloads. After that, users are able to define their own models with different architectures. --- [Visit Topic](https://discuss.tvm.apache.org/t/discussion-a-technical-approach-to-l

Re: [apache/tvm] [Release] v0.13.0 release schedule (Issue #15134)

Thanks @ysh329. Happy to help with things that need permissions! -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/15134#issuecomment-1600920350 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.12.0.rc0 (Issue #14710)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/14710#issuecomment-1537105639 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [COMMUNITY] Add new key for release signing (PR #14772)

Merged #14772 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/pull/14772#event-9175712298 You are receiving this because you are subscribed to this thread. Message ID:

[apache/tvm] [COMMUNITY] Add new key for release signing (PR #14772)

Adds Siyuan's key for release signing. cc @junrushao @tqchen You can view, comment on, or merge this pull request online at: https://github.com/apache/tvm/pull/14772 -- Commit Summary -- * [COMMUNITY] Add new key for release signing -- File Changes -- M KEYS (59) -- Patch Links --

[apache/tvm] Pre-release v0.12.0.rc0 - Apache TVM v0.12.0

# Introduction The TVM community has worked since the v0.11.1 release to deliver the following new exciting improvements! The main tags are below (**bold text is with lots of progress**): - Community, RFC; - Runtime: ACL(ArmComputeLibrary), Adreno, OpenCL & CLML, ROCm, CUDA & CUTLASS & TensorR

Re: [apache/tvm-rfcs] [RFC] SparseTIR Dialect (PR #100)

Thanks @yzh119. This RFC looks good to me. Looking forward to the 100th RFC being merged :) -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/100#issuecomment-1514009320 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [Release] v0.12.0 Release Candidate Notes (Issue #14645)

Please merge: - `TensorIR -> TIR` - `PyTorch -> Frontend` - `wasm -> web` - `transform, tophub, roofline, vta, rpc -> misc` -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/14645#issuecomment-1512349720 You are receiving this because you are subscribe

Re: [apache/tvm] [Release] v0.12.0 release schedule (Issue #14505)

@ysh329 tag `v0.13dev0` created -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/14505#issuecomment-1501407005 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [Release] v0.12.0 release schedule (Issue #14505)

I helped create the `v0.12.0` branch and will set the tag after the next commit merges. Could you please also send a PR to update the dev version like the commit https://github.com/apache/tvm/pull/14241 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/1

Re: [apache/tvm] [Release] v0.12.0 release schedule (Issue #14505)

Thanks @ysh329 Happy to see volunteers for the quarterly. Please fix the following issue of the post > a tag `v0.12.dev0` to be created, marking the beginning of the next > development cycle typo, should be `v0.13.dev0` > Note: for this specific release, given we'll have the end of the year pe

Re: [apache/tvm] [VOTE] Release Apache TVM v0.11.1 (Issue #14260)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/14260#issuecomment-1463543403 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC] Introduce PresburgerSet (PR #99)

Thanks, @multiverstack-intellif for the proposal and @tqchen @vinx13 's review. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/99#issuecomment-1447774121 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC] Introduce PresburgerSet (PR #99)

Merged #99 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/99#event-8624067076 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC] Further Unify Packed and Object in TVM Runtime (PR #97)

This RFC is merged now. Thanks @tqchen for the proposal and the reviews from @leandron @Mousius @cyx-6 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/97#issuecomment-1447772441 You are receiving this because you are subscribed to this thread. Mess

Re: [apache/tvm-rfcs] [RFC] Further Unify Packed and Object in TVM Runtime (PR #97)

Merged #97 into main. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/97#event-8624055152 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [VOTE] Release Apache TVM v0.11.0.rc0 (Issue #14129)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/14129#issuecomment-1445703837 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC] Introduce PresburgerSet (PR #99)

Thanks for everyone's input. We are going to merge in 24 hours if there are no additional comments. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/99#issuecomment-1445703115 You are receiving this because you are subscribed to this thread. Message

Re: [apache/tvm-rfcs] [RFC] Further Unify Packed and Object in TVM Runtime (PR #97)

Thanks for everyone's input. We are going to merge in 24 hours if there are no additional comments. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/97#issuecomment-1445703012 You are receiving this because you are subscribed to this thread. Message

Re: [apache/tvm-rfcs] [RFC] Further Unify Packed and Object in TVM Runtime (PR #97)

The comments so far seem have been addressed, would love to see if we have additional comments, and move forward on this -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/97#issuecomment-1431459868 You are receiving this because you are subscribed to t

Re: [apache/tvm-rfcs] [RFC] Introduce PresburgerSet (PR #99)

Let's keep it open for one week for enough visibility 😄 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/99#issuecomment-1430702535 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

Hi all, as suggested in the thread, we held this thread for a while. And now it can be a good time to come back. Let me summarize the previous discussion here: - Scoped module A scoped module (S0-module) can be: > - Clearly isolated in its own namespace. > - Clearly needed by some users in

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

@mbaret > I don't think it's fair or accurate to dismiss legitimate concerns of > community contributors as 'subjective'. @areusch has already enumerated in > some detail an 'objective' list of impacts that an S0 module can have on the > wider project. I think at a minimum we should be address

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

Hi, @areusch Thank you, for posting the analysis of the benefits and drawbacks of merging a module. I would like to point out that there are a few critical pieces that are missing (mainly on the community side): - Welcome new contributors who would become an added force, these contributors als

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

@mbaret > TOSA/Linalg are both graph dialects, but they don't fulfill the same function The definition of "same" is subjective; of course, different people can have different opinions that are less grounded. For example, what if many, or even the majority of people think a proposal contains su

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

## S1-level module There are a few suggestions for clarifying the S1-level module. An S1-level module is a module that does not follow the restrictions outlined in the S0. Specifically, an S1-level module is usually used as dependencies by other major modules in the project. The consideratio

Re: [apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

Thanks for the input and feedback from the community. Here I'd like to clarify some questions. For @areusch > As the RFC stands now, a committer could simply go and -1 each following PR > if they wanted to Note that the reviews of each PR are brought to their own context, and we anticipate g

[apache/tvm-rfcs] [Process RFC] Empowering New Scoped Module to the Project (PR #95)

In this process RFC, We'd like to propose a process to encourage scoped modules and set expectations about what we anticipate in such inclusion. [rendered] (https://github.com/Hzfengsy/tvm-rfcs/blob/empowering-new-scoped-module/rfcs/0095-empowering-new-scoped-module.md) [discuss thread](https:/

Re: [apache/tvm] [VOTE] Release Apache TVM v0.10.0.rc0 (Issue #13026)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/13026#issuecomment-1276961044 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm] [release] v0.10.0 Release Schedule (Issue #12832)

@zhyncs Thanks for your interest. Relax is at the RFC stage (https://github.com/apache/tvm-rfcs/pull/89). And we will upstream it when the RFC passes. -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/12832#issuecomment-1263234456 You are receiving this

Re: [apache/tvm] [VOTE] Establish TVM Unity Connection Technical Strategy (Issue #12651)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/12651#issuecomment-1231816769 You are receiving this because you commented. Message ID:

Re: [apache/tvm] [VOTE] Commit Messages RFC (Issue #12583)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/12583#issuecomment-1226697426 You are receiving this because you are subscribed to this thread. Message ID:

Re: [apache/tvm-rfcs] [RFC] Establish TVM Unity Connection -- A Technical Strategy (PR #91)

Thanks @tqchen!!! I'm excited to see the pre-RFC become this formal RFC. The Unity Connection is a great step from multi-level lowering compilation to a flexible, unified abstraction for the end-to-end model compilation. I'd like to summarize the [discuss thread](https://discuss.tvm.apache.or

Re: [apache/tvm-rfcs] [RFC] Relax Upstreaming (PR #89)

Thanks @leandron and @ekalda for the comments. We all agree that we are trying to improve the graph-level IR of TVM while the controversial point is that if we can enhance relay to support features from relax. Let's discuss it directly and focus on the technical points themselves. First of all

Re: [apache/tvm-rfcs] Inclusive Language RFC (#68) (PR #68)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm-rfcs/pull/68#issuecomment-1121769448 You are receiving this because you are subscribed to this thread. Message ID:

[Apache TVM Discuss] [Development/pre-RFC] Export TIR to json

Thanks, @SebastianBoblestETAS. I agree that json is a great format for serializing, but I have a few questions: 1. What are the pros and cons of json format compared with TVMScript (if we have python env) 2. How to design a json format to store all TIR information for all possible nodes? Do

Re: [apache/tvm] [VOTE] Replace codeowners with more relevant automation (Issue #10471)

+1 -- Reply to this email directly or view it on GitHub: https://github.com/apache/tvm/issues/10471#issuecomment-1061312750 You are receiving this because you are subscribed to this thread. Message ID:

[Apache TVM Discuss] [Development] Problem with FuseOps (and embedded constants in TIR)

I'm not sure. But I guess it is because C++ doesn't have a native fp16 type support? --- [Visit Topic](https://discuss.tvm.apache.org/t/problem-with-fuseops-and-embedded-constants-in-tir/12165/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe fr

[Apache TVM Discuss] [Development/pre-RFC] [RFC][Runtime] Bring `PackedFunc` into TVM Object System

Thanks @cyx. The RFC looks good to me. Looking forward to a formal RFC and following PR. --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-runtime-bring-packedfunc-into-tvm-object-system/11816/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscri

Re: [apache/tvm] [VOTE] Release Apache TVM v0.8.0.rc0 (Issue #9504)

+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-967779289

[Apache TVM Discuss] [Development/pre-RFC] [RFC] Hybrid Script Support for TIR

The tutorial PR is on: https://github.com/apache/tvm/pull/9315 Comments and suggestions are welcomed --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-hybrid-script-support-for-tir/7516/38) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe fro

Re: [apache/tvm-rfcs] [RFC] Update script block syntax (#41)

Thanks @junrushao1994. The reference has updated. -- 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-rfcs/pull/41#issuecomment-937708016

[apache/tvm-rfcs] [RFC] Update script block syntax (#41)

It's the rfc for a new block syntax in TVMScript. Co-authored-by: Junru Shao Co-authored-by: Zihao Ye Co-authored-by: Tianqi Chen You can view, comment on, or merge this pull request online at: https://github.co

Re: [apache/tvm-rfcs] [RFC][TVMScript] New namespace for tvmscript (#36)

Thanks, @altanh. Your suggestion makes sense to me. To be specific, here are two cases: parse from a python script and string. 1. When we parse from a python script, we detect the prefix `T` from the python env (through function `__globals__`, i.e. you can even use `XXX.block` if with `from tvm.

[apache/tvm-rfcs] [RFC][TVMScript] New namespace for tvmscript (#36)

It's a rfc for changing TVMScript namespace to enable auto-completion support and pass pylint checks @tqchen @junrushao1994 @tkonolige You can view, comment on, or merge this pull request online at: https://github.com/apache/tvm-rfcs/pull/36 -- Commit Summary -- * https://github.com/apach

Re: [apache/tvm] [VOTE] Adopt round-robin assignment of reviewers for GitHub pull request reviewer assignment. (#9057)

+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/9057#issuecomment-923534664

Re: [apache/tvm] [Release] v0.8 Release Planning (#8976)

Thanks for the work. I believe v0.8 is a good chance to land TensorIR scheduling (https://github.com/apache/tvm/issues/7527). Also, I will try my best to contribute some initial TensorIR tutorials and documentations before the v0.8 release. -- You are receiving this because you are subscribed

Re: [apache/tvm] [VOTE] Adopt New Code Review Guideline (#8928)

+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/8928#issuecomment-913092760

Re: [apache/tvm] [RFC][Tracking Issue] TensorIR Scheduling (#7527)

Hey @manupa-arm, Don't worry. We will make TensorIR be an optional but not the default backend of relay as our first step. There must be many works (including meta schedule and some corner cases that meta schedule can not generate automatically) to do before totally switching TE to TensorIR.

Re: [apache/tvm] [RFC][Tracking Issue] TensorIR Scheduling (#7527)

Thanks, @manupa-arm. Of course, we will! The ultimate goal of TensorIR is to replace the current TE schedule. Before integrating it to `relay`, we need to finish all of our M2 items (there are only two left). Here are the following steps: - TensorIR docs and tutorial - Relay integration - Met

[Apache TVM Discuss] [Development/pre-RFC] Updated Docs pre-RFC

Thanks, @hogepodge. It's a good opportunity for us to enhance TVM documentation and tutorials together. I want to share some of my thoughts on it. ## A Separated Developer Documentation Users(who will use TVM as a tool to compile models on supported models and backends and won't change much of

[Apache TVM Discuss] [Development] [Dynamic Shape] Better simplify support for dynamic boundary check

Thanks for the proposal. I agree that it is a valuable problem for dynamic shape. Here are two questions from me: 1. Is it necessary to rewrite `(d1*d2)*d0` into `d0*d1*d2`. Can we prove them equal by `Analyzer` directly? 2. Can we embed the new rule into `tir.Simplify` rather than create a n

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Thanks for such a great suggestion. Yes, we do support IRBuilder for TensorIR. However, it is not recommended. Because it is likely to generate illegal or opaque IR (which lacks some of the information). Besides, there are so many attributes/annotations (e.g block read/write regions and block

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Thanks, @yzh119. Currently, we have not considered the cross-kernel schedule in TensorIR. But it may be possible if we make it as one large kernel. Could you please show an example? (e.g. the IR before and after the schedule) --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tensorir

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Thank you for such a valuable question. Your understanding is correct. We still need a schedule language to schedule. That is because we need a simple API and abstraction for both human experts and automatical optimization (like AutoTVM, Ansor, and our new meta-schedule). Also, we try to kee

[Apache TVM Discuss] [Development/RFC] [RFC] Rename Hybrid Script

`tvm.script` would be a great name --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-rename-hybrid-script/7915/6) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Technically, it should support. However, due to time constraints, we have not yet supported. --- [Visit Topic](https://discuss.tvm.apache.org/t/rfc-tensorir-a-schedulable-ir-for-tvm/7872/25) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from th

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Thank you for your interest. Tensorize in TensorIR is completely different from the TE ones. In TensorIR, we use two functions (desc_func and intrin_func) to define an intrinsic. Here would be an example of intrinsic (Note that TensorIR is still WIP, so the API may be changed). ```python @

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Good questions! 1. As for as we know, we would like to let users use TensorIR schedule rather than TE schedule one we fully upstream the TensorIR. For three reasons: 1. Just as you have mentioned, TE is a fronted wrapper, and it directly generates TIR with blocks. Somehow, TE is more like

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

Thank you for your interest. A1: Current op fusing is based on `stage` but the critical point is fusing the injective computation. We can also inline injective computation by `traverse_inline`. So there is no doubt that FuseOps works. As for the philosophy, I think there are only few changes

[Apache TVM Discuss] [Development/RFC] [RFC] TensorIR: A schedulable IR for TVM

## Background and Motivation TVM is an end-to-end deep learning compiler with two levels of IR and optimization. TVM translates popular DL frameworks into Relay and optimizes the computation graph, after which it lowers each graph node into Tensor Expression(TE) and does another function-level

[TVM Discuss] [Development/RFC] [RFC][Tensor Core] Optimization of CNNs on Tensor Core

You are right. Thank you for figuring out the bug. That's would be my fault that I focused on the classical workload (e.g. resnet), but forgot to test large shapes. It's easy to fix. Can you please create a PR? --- [Visit Topic](https://discuss.tvm.ai/t/rfc-tensor-core-optimization-of-cn

Re: [dmlc/tvm] [RFC] Tensor Core Support (#4052)

Closed #4052. -- 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/4052#event-2753595541

Re: [dmlc/tvm] [RFC] Tensor Core Support (#4052)

I have chatted with @minminsun and his team these days. Just as then mentioned https://github.com/dmlc/tvm/issues/4105#issuecomment-542032766. We can have different frontends but only one backend. In my previous implement, users can only use fragments with 16x16x16 shape and row-major layout. To

Re: [dmlc/tvm] [RFC] Auto TensorCore CodeGen (#4105)

Thank you for the RFC. It is complete TensorCore support. It is nice that you can support different types and different data layouts, which is not supported in my solution currently. ## Lower Passes vs Intrinsic Intrinsic is a tool for describing what instructions can be done in specific hardwa

Re: [dmlc/tvm] [RFC] Tensor Core Support (#4052)

@soiferj Thank you for such a helpful comment. I have just made the extension into the schedule for BatchMatMul. You can check the schedule in my fork repo: https://github.com/Hzfengsy/tvm/blob/master/tests/python/unittest/test_schedule_tensor_core.py#L101 -- You are receiving this because you

Re: [dmlc/tvm] [RFC] Tensor Core Support (#4052)

@yangjunpro Really happy to see another solution for TensorCore. You are right! I just extend tvm intrinsic to support it. It does cause programmers who write the schedule some trouble. It is not easy to write a high-performance schedule. I'm really curious about how to use IR passes to recogn

Re: [dmlc/tvm] [RFC] Tensor Core Support (#4052)

@tmoreau89 Exactly! For now, we use the NCHWnc layout, the same layout with VTA. -- 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/4052#issuecomment-537816661

  1   2   >