December 15 - TVM Tutorial Day

TitleTime (PST)TrackSpeakersOrganization
TVM User Tutorials8:55 amMain StageSpeakers: Organization: The Apache TVM Community
TVM Developer Tutorials8:55 amOpen Source LoungeSpeakers: Organization: The Apache TVM Community
Introduction to TVM with TVMC: A Command-Line Driver for TVM9:00 amUser TutorialSpeakers: Leandro Nunes
Gustavo Romero
Organization: Arm, Linaro
TVM Developer Bootcamp – Overview9:00 amDeveloper TutorialSpeakers: Josh FrommOrganization: OctoML
TVM Developer Bootcamp – Frontends9:30 amDeveloper TutorialSpeakers: Josh FrommOrganization: OctoML
TVM Developer Bootcamp – Operators10:00 amDeveloper TutorialSpeakers: Josh FrommOrganization: OctoML
Introduction to TVM with the Python/TVMC Interface10:30 amUser TutorialSpeakers: Jocelyn ShiueOrganization: OctoML
TVM Developer Bootcamp – Writing Hardware Backends10:30 amDeveloper TutorialSpeakers: Eric LunderbergOrganization: OctoML
Understanding TensorIR: An Abstraction for Tensorized Program Optimization11:00 amUser TutorialSpeakers: Siyuan FengOrganization: Shanghai Jiao Tong University
Neural Network Quantization with Brevitas11:15 amDeveloper TutorialSpeakers: Alessandro PappalardoOrganization: Xilinx Research
Build on AWS for Startups Overview12:15 pmDeveloper TutorialSpeakers: AWS Organization: AWS
Using Swift and Apache TVM to Develop ML Apps for the Apple Ecosystem12:45 pmUser TutorialSpeakers: Iliya SlavutinOrganization: Deelvin Solutions
Optimizing ML Models for Arduino with microTVM1:00 pmUser TutorialSpeakers: Gavin UbertiOrganization: OctoML
Automating and Simplifying MLPerf Inference Benchmark Submissions with TVM and CK2:00 pmUser TutorialSpeakers: Grigori Fursin
Thomas Zhu
Alexander Peskov
Organization: OctoML

December 16 - TVMCon Day 1

TitleTime (PST)TrackSpeakersOrganization
Keynote and Community Update9:00 amMain StageSpeakers: Tianqi Chen
Jared Roesch
Denise Kutnick
Organization: OctoML
Growing from “Neat Project” to “Industry Leader”9:50 amMain StageSpeakers: Sarah NovotnyOrganization: Microsoft Azure Office of CTO
How do we Responsibly Democratize Transformers, the Most Impactful Tech of the Decade?10:15 amMain StageSpeakers: Clément DelangueOrganization: Hugging Face
Break10:30 amMain StageSpeakers: Organization:
TVM at Xilinx: Compiling for Versal AI Engines10:40 amMain StageSpeakers: Jorn TuylsOrganization: Xilinx
TVM at Arm11:00 amMain StageSpeakers: Steve RoddyOrganization: Arm
Deep Learning Model Training at AWS11:20 amMain StageSpeakers: Yida WangOrganization: Amazon Web Services
PyTorch AOTAutograd: A pythonic extension point for integrating compilers into PyTorch training11:40 amMain StageSpeakers: Horace HeOrganization: Meta
Lunch Break12:00 pmMain StageSpeakers: Organization:
Sponsor Booths Open12:00 pmOpen Source LoungeSpeakers: Organization: TVMCon Sponsors
Machine Learning Compilers: Bringing ML to the Edge12:45 pmMain StageSpeakers: Chip HuyenOrganization: Stealth Startup and Stanford University
Miniaturizing Models for microNPUs: a Cascading Scheduler for TVM12:45 pmEdge & Embedded LoungeSpeakers: Matthew BarrettOrganization: Arm
TVM Unity Community Session12:45 pmOpen Source LoungeSpeakers: Jared RoeschOrganization: OctoML
Lightning Quick Performance on Apple M1 with TVM1:10 pmMain StageSpeakers: Phil MazenettOrganization: OctoML
Better Tensor Core Support in TVM with CUTLASS1:15 pmOpen Source LoungeSpeakers: Leyuan Wang
Andrew Kerr
Organization: Bytedance
Unified Static Memory Planner (USMP)1:15 pmEdge & Embedded LoungeSpeakers: Manupa Karunaratne
Dmitriy Smirnov
Organization: Arm
TVM in the Arene AI Platform of Woven Planet1:20 pmMain StageSpeakers: Ryo TakahashiOrganization: Woven Planet Holdings, Inc.
Transparent TVM Backend Acceleration1:35 pmMain StageSpeakers: Tiejun ChenOrganization: VMWare
Integrating the Synopsys DSP-enhanced ARC Processors into TVM1:40 pmEdge & Embedded LoungeSpeakers: Kuen-Wey Lin
David Wang
Chuck Pilkington
Organization: Industrial Technology Research Institute, Synopsys
Common Subexpression Elimination for TIR1:45 pmOpen Source LoungeSpeakers: Franck SlamaOrganization: Qualcomm
TVM Streamer – Accelerating Multimedia Framework with TVM1:50 pmMain StageSpeakers: Cecilia Albertsson
Hiroki Endoh
Shinya Kaji
Organization: Fixstars Corporation, NTT TechnoCross Corporation
TVM with PaddlePaddle2:05 pmMain StageSpeakers: Jiajun Jiang
Yuguang Deng
Yin Ma
Organization: Baidu
RAZOR: Relay via PyTorch Lazy Tensor2:15 pmOpen Source LoungeSpeakers: Haozheng FanOrganization: Amazon
TVM at Marvell2:20 pmMain StageSpeakers: Derek Chickles
Chien-Chun (Joe) Chou
Organization: Marvell, Machine Learning Software
Break2:30 pmMain StageSpeakers: Organization:
DietCode: Automatic Optimization for Dynamic Tensor Programs2:30 pmOpen Source LoungeSpeakers: Bojian Zheng
Ziheng Jiang
Organization: University of Toronto
Lightning Talks – Compilation and Optimization2:40 pmLightning TalksSpeakers: VariousOrganization: The Apache TVM Community
Puffin: A MLIR-based tensorizer for training2:40 pmLightning TalksSpeakers: Liangfu ChenOrganization: Amazon Web Services
Verifiable Compilation to Accelerators Using a Formal Software/Hardware Interface and Flexible Matching2:46 pmLightning TalksSpeakers: Gus SmithOrganization: University of Washington
Automatic Tensorized Program Optimization2:52 pmLightning TalksSpeakers: Bohan HouOrganization: Carnegie Mellon University
Tsunami: Training in TVM with Relay2:58 pmLightning TalksSpeakers: Altan HaanOrganization: OctoML
R-TVM, a polyhedral mapper for TVM3:04 pmLightning TalksSpeakers: Benoit MeisterOrganization: Reservoir Labs
Fuzzing TVM Relay3:10 pmLightning TalksSpeakers: Steven LyubomirskyOrganization: University of Washington
RoofTune:Accelerating the Tuning Process Based on Roofline Model3:16 pmLightning TalksSpeakers: Hui Zhong
Haiwen Fu
Xiaohua Shi
Organization: Beihang University
SONAR: Direct architecture and system optimization search3:22 pmLightning TalksSpeakers: Elias JaasaariOrganization: Carnegie Mellon University
Collage: Automated Integration of Deep Learning Backends3:28 pmLightning TalksSpeakers: Byungsoo JeonOrganization: Carnegie Mellon University
The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding3:34 pmLightning TalksSpeakers: Pratik FegadeOrganization: Carnegie Mellon University
Multi-stream Support for Virtual Machine Executor3:40 pmLightning TalksSpeakers: Yaoyao DingOrganization: University of Toronto

December 17 - TVMCon Day 2

TitleTime (PST)TrackSpeakersOrganization
Keynote and Community Update9:00 amMain StageSpeakers: Luis Ceze
Jason Knight
Vanessa Yan
Sameer Farooqui
Organization: OctoML
Green AI9:50 amMain StageSpeakers: Jesse Dodge
Oren Etzioni
Organization: Allen Institute for AI
Monitoring ML on the Edge10:10 amMain StageSpeakers: Alessya VisnjicOrganization: WhyLabs
Break10:30 amMain StageSpeakers: Organization:
Nexus: A TVM-based Inference Server10:40 amMain StageSpeakers: Loc HuynhOrganization: Microsoft
The Torch-MLIR Project10:55 amMain StageSpeakers: Sean SilvaOrganization: Google
TVM For Snapdragon Mobile Platform11:10 amMain StageSpeakers: Jeff GehlhaarOrganization: Qualcomm
Efficient Application Mapping in a Heterogeneous Environment using TVM11:25 amMain StageSpeakers: Joey Chou
Alicja Kwasniewska
and Sharath Raghava
Seamless Cross Platform Deployment for Communities11:40 amMain StageSpeakers: Wilson Yu
Mei Ye
Amir Khojaste Galeshkhale
Organization: AMD
Lunch Break12:00 pmMain StageSpeakers: Organization:
Sponsor Booths Open12:00 pmOpen Source LoungeSpeakers: Organization: TVMCon Sponsors
Improvements to TVM Developer Productivity12:45 pmOpen Source LoungeSpeakers: Andrew ReuschOrganization: OctoML
TVM at Tencent12:45 pmMain StageSpeakers: Wenxi ZhuOrganization: Tencent
Reflections on microTVM on Cortex-M12:45 pmEdge & Embedded LoungeSpeakers: Chris SidebottomOrganization: Arm
TPAT: TensorRT Plugin Autogen Tool1:05 pmMain StageSpeakers: Qian QiuOrganization: Tencent
Lightweight Profiling for TVM1:15 pmOpen Source LoungeSpeakers: Jyotsna VermaOrganization: Qualcomm
How to Use FP16 Quantization in TVM1:15 pmEdge & Embedded LoungeSpeakers: Andrew LuoOrganization: OctoML
ONNX, ONNX Runtime, and TVM1:20 pmMain StageSpeakers: Manash Goswami
Ganesan Ramalingam
Organization: Microsoft
TVM at EdgeCortix – Heterogenous AI Hardware Acceleration1:35 pmMain StageSpeakers: Antonio TomasOrganization: EdgeCortix Inc.
TVM-Enabled Realtime Character Control for Mobile Games1:45 pmOpen Source LoungeSpeakers: Haidong LanOrganization: Tencent
VTA++: Expanded Design Space Exploration with an Enhanced Versatile Tensor Accelerator1:45 pmEdge & Embedded LoungeSpeakers: Abhijit DavareOrganization: Intel Labs
Relax: Co-Designing High-Level Abstraction Towards TVM Unity1:50 pmMain StageSpeakers: Yuchen Jin
Altan Haan
Ziheng Jiang
Organization: OctoML
microTVM in 20212:10 pmMain StageSpeakers: Andrew Reusch
Mehrdad Hessar
Organization: OctoML
Apple BNNS Integration, Benefits and Challenges2:15 pmOpen Source LoungeSpeakers: Alexander PeskovOrganization: Deelvin Solutions
Break2:30 pmMain StageSpeakers: Organization:
Lightning Talks – Edge and Embedded2:40 pmLightning TalksSpeakers: VariousOrganization: Apache TVM Community
Extremely Fast GEMM on AVX512 CPUs Combining TVM and XSMM2:40 pmLightning TalksSpeakers: Honglin ZhuOrganization: Tencent Holding Limited
A Simulation-Based TVM Extension for Auto-Tuning in the Early Design Phases2:46 pmLightning TalksSpeakers: Yannick Braatz
Michael J. Klaiber
Axel J. Acosta
Organization: Robert Bosch GmbH
Leveraging TVM as a front-end compiler for RISC-V based custom tinyML processor2:52 pmLightning TalksSpeakers: Vaibhav VermaOrganization: University of Virginia
Integrate TVM With MediaTek NeuroPilot for Mobile Devices2:58 pmLightning TalksSpeakers: Robert Lai
Chun-Ping Chung
Organization: Mediatek
Caffe-SSD Inference on Edge Device Using TVM and Hybrid Script3:04 pmLightning TalksSpeakers: Masahiro HiramoriOrganization: Mitsubishi Electric Corporation
Support sparse and irregular workloads in TIR3:10 pmLightning TalksSpeakers: Zihao Ye
Ruihang Lai
Organization: University of Washington
Optimization with TVM Hybrid OP on RISC-V with P Extension3:16 pmLightning TalksSpeakers: Lee Jenq-Kuen
Yu Meng-Shiun
Yuan Chuan-Yue
Organization: National Tsing Hua University, Taiwan
Integer Only Quantization and Pruning of Transformers3:22 pmLightning TalksSpeakers: Amir Gholami
Sehoon Kim
Organization: UC Berkeley
Another Automatic Kernel Generator on Huawei NPU with Polyhedral Compilation3:28 pmLightning TalksSpeakers: Shenghu Jiang
Mingli Sun
Organization: Beihang University
Extending auto-scheduler to support performance evaluation with timing model3:34 pmLightning TalksSpeakers: Minchun Liao
Yaohua Chen
Chungta King
Organization: National Tsing Hua University, Industrial Technology Research Institute (ITRI)
TVM at Qualcomm Adreno3:40 pmLightning TalksSpeakers: Siva Rama KrishnaOrganization: Qualcomm India Pvt Ltd

Register for TVMCon 2021