Repository navigation
[DEV] TVM v0.6 Roadmap #2623
Description
Activity
Does runtime for dynamic model refer to the runtime for Relay? Otherwise, we can also add Relay runtime into 0.6 roadmap.
@edmBernard Great to hear that! Added!
@icemelon9 Right, it refers to the runtime for Relay
Wish TVM v0.6 can finish this item: #2351. i.e. Support importing exist quantization TFLite model. This can be a start for supporting importing existing quantization model (i.e. don't restrict TFLite).
Reacted by Ziheng Jiang, chenyaofo, Sloth, Hawk Zhou and LinkTsangPass manager for relay, should be able to finish discussion soon, haha
Reacted by Zhao Wu, Yida Wang, Wei Chen, Ziheng Jiang, Yong Wu and Haichen Shen@yzhliu I think so. It is a legacy item from roadmap v0.5
- pinned this issue
on Feb 19, 2019 Will work together with @icemelon9 on dynamic runtime.
Reacted by Yida Wang, Zhi, Haichen Shen, Ziheng Jiang, radao, Tianyi, daweili1226 and Ehsan M. KermaniI think we should also deprecate nnvm fully in 0.6. So far there are still some legacy code in topi depends on nnvm.
Could we also add
Anydimension support in Relay to the roadmap? I think it's an important feature to have.Reacted by Wei Chen and Jared RoeschI think official text format support should be part of 0.6. i.e. the parser and printer should be able to support all Relay constructs.
TVM Monthly - Feb 2019
Community
In Feb 2019, we successfully released TVM v0.5 (release notes) and made the roadmap for v0.6.
The community welcomes new Reviewer Zhao Wu (@FrozenGene), Committer Jared Roesch (@jroesch) and PMC member Lianmin Zheng (@merrymercy)
TVM community has voted through Apache Incubation proposal (#2543). Markus Weimer posted a proposal to general@incubator.apache.org seeking for ideas and suggestions. The official voting is ongoing on general@ right now.
Features and Improvements
Operator Support
- A special operator
annotation.stop_fusionto prevent it being fused with previous expressions ([RELAY] Stop_fusion annotation #2624). batch_matmulsupported (#2561).reverse_reshapesupported (#2503).- Faster-RCNN proposal operator for CUDA (#2420).
- Vision operator for YOLO
yolo_reorg(#1941). sliceoperator for MXNet (#2662).arangesupported (#2621).- Vision operator
roi_align(#2618). whereoperator for MXNet (#2647).
User Interface and Frontend
- Introduced
HybridModule(#2477) so that normal TVM schedule can be compiled to hybrid target, run and dumped to Hybrid Script. - Most frameworks have been supported in Relay, including ONNX, Keras, Tensorflow, Caffe2, CoreML, NNVMv1, MXNet (#2246). Siju is working on DarkNet.
- Relay now supports saving and loading parameter dictionaries. (#2620)
- Rust frontend (#2292).
- We are now supporting Tensorflow saved model for NNVM (#2493). Relay support is ongoing (#2586).
- Add
max_num_threadsto Hybrid Script, which allows users to get max number of threads for GPU targets (#2672).
Runtime and Hardware Support
- RFC for bringing TVM to Bare-Metal devices (#2563)
- Make external library extend TVM's NDArray more easily (#2613).
Performance Improvement
- AlterOpLayout pass is now enabled for x86 on Relay (#2585). It is essential to get decent performance for CNN-based model on Intel CPUs.
Documents and Tutorials
- Tutorials for deep learning frameworks support in Relay.
- Tutorial for running AutoTVM with Relay (#2594).
- Document for Algebraic Data Types (#2575).
High-level Optimizations
- An optimization pass to eliminate expressions which have the same functionality and same inputs (#2639).
- Provided a pass to calculate the number of multiply-accumulate operations in a network (#2609).
- Algebraic Data Types (ADT) support (#2442, #2575). ADT provides an expressive, efficient, and safe way to realize recursive computation (e.g., RNN). Refer to https://docs.tvm.ai/langref/relay_adt.html for more information.
- As a part of Relay's automatic differentiation system, we are adding primal gradients for Relay operators. Please refer to #2562 for tracking the progress. (Help wanted). For automatic differentiation in Relay, also see Automatic differentiation for tensor expressions, Higher order reverse mode automatic differentiation that work with control flow, Tensor Expression level automatic differentiation
- Low-bit quantization supported (#2116). The workflow includes annotation, calibration and transformation. Please also see Data-Aware Calibration for calibration algorithm improvement (Help wanted).
Tensor Expression
- RFC for formalizing Integer Arithmetic Analysis (#2588). It is aiming to perform better context-dependent analysis, bound analysis, centralized arithmetic logic and arithmetic simplification.
Contribution and Commits
Thanks Wei @wweic or providing the tools.
People Who Reviewed Pull Requests
- tqchen Runtime, Relay, Tensor Expression, Document, Frontend, AutoTVM
- were Runtime, Hybrid Script, TOPI
- junrushao1994 Runtime, Relay, Hybrid Script
- ZihengJiang Relay, Rust, Quantization, Tensor Expression
- sgrechanik-h Tensor Expression
- derisavi Tensor Expression
- wweic Relay
- nhynes Rust, Quantization
- ehsanmok Rust
- mjs-arm Pylint
- MarisaKirisame Relay
- srkreddy1238 Relay, Tensorflow Frontend, Golang
- vinx13 Hybrid Script, Relay, TOPI, Quatization
- kazum Relay
- FrozenGene TFLite Frontend, AutoTVM, Quantization
- jroesch Relay, Rust
- zhiics Relay, Runtime, Tensorflow Frontend
- imorinaga Relay(heterogenous annotation)
- merrymercy AutoTVM, Tensor Expression, Quantization
- yzhliu AutoTVM, Relay, Tensor Expression, Frontend
- eqy AutoTVM, Quantization, Relay
- icemelon9 AutoTVM, Tensor Expression, Runtime, Relay, Frontend
- reminisce Runtime
- kevinthesun Tensor Expression, TOPI
- Anthony-Mai Tensor Expression
- slyubomirsky Relay
- joshpoll Relay Document
- eric-haibin-lin Bugfix
- ZhennanQin Bugfix
- grwlf Runtime
- xqdan Tensor Expression, Hybrid Script
- Laurawly Relay, Hybrid Script, TOPI
- masahi Relay, TOPI, Document, CodeGen
- siju-samuel Relay
- PariksheetPinjari909 Operator
- liangfu Quantization
- lixiaoquan Quantization
- ajtulloch Quantization
- zhreshold Operator
People Who Committed
- tqchen CI, Runtime, Tensor Expression, Relay Text Printer
- ruslo Documents
- mjs-arm Pylint, CI
- vinx13 Relay, TOPI, Operator
- lixiaoquan Relay
- wweic Relay Document
- kazum Tutorial and Document
- derisavi Tensor Expression (IntSet)
- antinucleon AutoTVM
- slyubomirsky Relay (ADT, AutoDiff)
- MarisaKirisame Relay
- junrushao1994 Runtime, Build
- were Hybrid Script
- yidawang Relay (MAC Calculation)
- ariwaranosai Operator
- ZihengJiang Relay, Quantization
- jroesch Relay
- hlu1 Runtime
- headupinclouds TOPI
- zhiics Relay, Tensor Expression
- weberlo Relay (param save/load)
- icemelon9 Tensor Expression, Operator
- yzhliu Tensor Expression
- eqy Relay, Quantization, AutoTVM tutorial
- geexie Bug-fix
- abergeron Conda package
- larroy NodeEntry Implement Improvement
- ptrendx Bug-fix
- Anthony-Mai Namespace Fix
- jdavies-huawei Tensor Expression
- srkreddy1238 Tensorflow Frontend, Golang
- yongwww Tensorflow Frontend, Relay Document
- alexeyr Code Improvement
- nhynes Rust
- makihiro Caffe2 Frontend
- kevinthesun AutoTVM
- Huyuwei Tutorial
- ehsanmok Rust
- siju-samuel Operator
- sgrechanik-h Tensor Expression
- haojin2 Operator
- SiNZeRo Document
- denis0x0D CodeGen
- Laurawly Bug-fix
- apivovarov Typo-fix
- take-cheeze Typo-fix
List of Commits
Reacted by Siju Samuel, Tianqi Chen, Yida Wang, Ehsan M. Kermani, Haichen Shen, Yong Wu and Json Lee- A special operator
11 remaining items
What is the planned release date for 0.6?
There has been quite a lot of improvements recently. While it is up to the community, I think we might be able to get out something around Sep
- graph level automated optimization
Does it mean traditional fusion / layout transform, or more recent graph substitution like this paper? If the later one, I would like to port my onnx implementation to TVM.
Higher order automatic differentiation was done like half years ago. Please check that.
TVM Monthly - July 2019
@MarisaKirisame Checked. I listed it here just because that it did not go into the last release cycle
Reacted by 霧雨魔理沙Hybrid python programming model
transition of vision operators to hybrid mode.what's plan for this feature?
TVM Monthly - August 2019
TVM Monthly - September 2019
When will we have 0.6 release ? thanks
TVM Monthly - October 2019
- unpinned this issue
on Nov 23, 2019
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.
Features