You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@tvm.apache.org by Tianqi Chen <no...@github.com> on 2020/02/08 19:29:50 UTC
[apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
This roadmap for TVM v0.6. TVM is a community-driven project and we love your feedback and proposals on where we should be heading. Please open up discussion in the discussion forum as well as bring RFCs.
- Feel free to volunteer yourself if you are interested in trying out some items(they do not have to be on the list).
- Please also check out the [help wanted](https://github.com/apache/incubator-tvm/issues?q=is%3Aissue+is%3Aopen+label%3A%22status%3A+help+wanted%22) list in the github issues on things that need help
In the 0.7 cycle, we are going to focus on the following four areas. Which are summarized summarized from the [forum discussion](https://discuss.tvm.ai/t/rfc-discuss-tvm-v0-7-roadmap/5159).
We also welcome contributions along all the other areas, including more operator and model coverages, and they will be added to this list gradually. Please reply to this thread about what you would like to volunteer to work on.
### Core Infra
- [ ] Unified IR refactor
- [ ] Unified runtime for heterogeneous execution
- [ ] Enhanced support for high-level graph rewriting for accelerators
- [ ] Improving test and benchmark infrastructure.
- [ ] Testing and benchmarking on remote targets.
### Usability
- [ ] Better documentations for developments
- [ ] Command line utilties to use TVM as an ahead of time compiler
- [ ] Visualization of Relay Graphs
### Backend and runtime
- [ ] End to end uTVM
- [ ] More dynamic model support
- [ ] Complete VM functionality
- [ ] Improve VM performance
- [ ] Add tutorial for VM
- [ ] External code generator
- [ ] End to end inference with Chisel VTA
- [ ] CUDA half2 data type support
- [ ] bfloat16 support
- [ ] 4-bit model support
### Automation
- [ ] More auto scheduling
- [ ] Better loop partitioning
- [ ] Reduce AutoTVM tuning time
- [ ] Auto tensorization
- [ ] Auto quantization
--
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/4845
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by shoubhik <no...@github.com>.
What is the expected time of release for this release? what are the chances of it happening in May?
--
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/4845#issuecomment-612762262
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Jon <no...@github.com>.
> Due to recent situation and the current progress, we might expect a bit of delay in the release to June/July -- we expect the unified IR refactor to land by then. We will do our best to keep the timeframe.
Including more operator should be scheduled as least for one frontend? Onnx or tensorflow or mxnet etc, it will be great if 'ONE' frontend is widely supported!!
--
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/4845#issuecomment-616974448
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Tianqi Chen <no...@github.com>.
Please see https://github.com/apache/incubator-tvm/issues/6421 for release plan
--
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/4845#issuecomment-688995236
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by masahi <no...@github.com>.
We will have a good support for pytorch including dynamic and quantized models. I have a series of PRs coming.
--
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/4845#issuecomment-583773717
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Tianqi Chen <no...@github.com>.
re relay c_api, there is no need to do so, as all the relay functions are exposed through the PackedFunc FFI. So all the features of relay can already be accessed through the tvm's C API.
--
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/4845#issuecomment-600253877
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Jared Roesch <no...@github.com>.
> I am currently working on some end-to-end model stuff, and Relay's optimization pass are too slow. Any plans on improving the compilation speed?
Can you identify why they are slow? For example switching some passes to the new iterative graph visitor might improve speed quite a bit. In previous profiling attempts I have found a significant amount of time is spent allocating, having a pooling allocator can often improve speeds quite a bit.
--
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/4845#issuecomment-591189423
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Jian Weng <no...@github.com>.
I am currently working on some end-to-end model stuff, and Relay's optimization pass are too slow. Any plans on improving the compilation speed?
--
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/4845#issuecomment-588516798
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Liangfu Chen <no...@github.com>.
I wonder is there any active effort working on the feature "Auto tensorization", and I'm interested in contributing.
--
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/4845#issuecomment-588125167
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Tianqi Chen <no...@github.com>.
@yangjunpro Perhaps it worth to start a new thread in the discuss forum to discuss MLIR related topics. We certainly would love some proposals about interpolation between MLIR and TVM.
--
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/4845#issuecomment-585290701
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Eli Tom <no...@github.com>.
External codegen integration with uTVM is highly interesting for us at CEVA.
We are looking at compiling networks using TVM and generating code with our implementation of codegen and then executing on CEVA hardware via uTVM.
The goal (beside getting it done) is to share via TVM github repo.
--
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/4845#issuecomment-584123110
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Tianqi Chen <no...@github.com>.
Due to recent situation, we might expect a bit of delay in the release to June/July. We will do our best to keep the timeframe.
--
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/4845#issuecomment-613014481
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Jun Yang <no...@github.com>.
Is there any plan to integrate TVM as a dialect into MLIR?
So other components based on MLIR can leverage the capability of TVM, such as high performance codegen, and fusion, etc.
--
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/4845#issuecomment-585288898
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Tianqi Chen <no...@github.com>.
@liangfu auto tensorization depends on on the new IR update, we will send out specific guidelines after we finish the IR refactoring
--
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/4845#issuecomment-588397980
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Seyyed Hossein Hasanpour <no...@github.com>.
Could you also add support for intel graphics as well. it seems it is not supported at the moment!
--
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/4845#issuecomment-584047567
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Yao Wang <no...@github.com>.
We will have general support for TensorFlow control flow and tensor array, which allows parsing for TensorFlow object detection models
--
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/4845#issuecomment-636151921
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by "Ehsan M. Kermani" <no...@github.com>.
I'd like to propose creating Relay `c_api.h` for further expansions from frameworks and bindings in the future.
--
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/4845#issuecomment-600205391
Re: [apache/incubator-tvm] [DEV] TVM v0.7 Roadmap (#4845)
Posted by Tianqi Chen <no...@github.com>.
@Coderx7 as far as i know, intel graphics is already supported for a limited setting by @Laurawly . @etom42 it would be great if you can start a RFC thread in the discus forum to keep the community aware of what you are working on -- it also brings chance for collaboration and give suggestions :)
--
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/4845#issuecomment-584249293