Канал: uwsampl

Optimal Kernel Orchestration for Tensor Programs with Korch - Muyan Hu

Optimal Kernel Orchestration for Tensor Programs with Korch - Muyan Hu

FlexGen:High-throughput Generative Inference of Large Language Models with a Single GPU - Ying Sheng

FlexGen:High-throughput Generative Inference of Large Language Models with a Single GPU - Ying Sheng

Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation

Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass Mutation

Tackling the Communication Bottlenecks of Distributed Deep Learning Training Workloads

Tackling the Communication Bottlenecks of Distributed Deep Learning Training Workloads

Verified Tensor-Program Optimization Via High-Level Scheduling Rewrites | SAMPL Talk 2022/04/21

Verified Tensor-Program Optimization Via High-Level Scheduling Rewrites | SAMPL Talk 2022/04/21

Alpa: Automating Inter- and Intra- Operator Parallelism for Distributed Deep Learning

Alpa: Automating Inter- and Intra- Operator Parallelism for Distributed Deep Learning

Resource-Efficient Execution of Deep Learning Computations | SAMPL Talk 2022/02/03

Resource-Efficient Execution of Deep Learning Computations | SAMPL Talk 2022/02/03

Synthesizing Programmable Accelerators: A Compiler’s Perspective | SAMPL Talk 2022/01/27

Synthesizing Programmable Accelerators: A Compiler’s Perspective | SAMPL Talk 2022/01/27

TensorIR: An Abstraction for Tensorized Program Optimization | SAMPL Talk 2022/01/20

TensorIR: An Abstraction for Tensorized Program Optimization | SAMPL Talk 2022/01/20

Autotuning Production Machine Learning Compilers | SAMPL Talk 2021/11/04

Autotuning Production Machine Learning Compilers | SAMPL Talk 2021/11/04

Decoupling Algorithm from Hardware Customizations for Software-Defined Reconfigurable Computing

Decoupling Algorithm from Hardware Customizations for Software-Defined Reconfigurable Computing

Large-scale GNN training with DGL | SAMPL Talk 2021/12/02

Large-scale GNN training with DGL | SAMPL Talk 2021/12/02

TVM Tutorial at FCRC [7/9]: Ultra-Low Bits Inference

TVM Tutorial at FCRC [7/9]: Ultra-Low Bits Inference

TVM Tutorial at FCRC [9/9]: Tutorial Conclusion

TVM Tutorial at FCRC [9/9]: Tutorial Conclusion

TVM Tutorial at FCRC [8/9]: Bring Your Own Datatype

TVM Tutorial at FCRC [8/9]: Bring Your Own Datatype

TVM Tutorial at FCRC [6/9]: Micro-TVM

TVM Tutorial at FCRC [6/9]: Micro-TVM

TVM Tutorial at FCRC [5/9]: SageMaker Neo

TVM Tutorial at FCRC [5/9]: SageMaker Neo

TVM Tutorial at FCRC [4/9]: TSIM

TVM Tutorial at FCRC [4/9]: TSIM

TVM Tutorial at FCRC [3/9]: VTA

TVM Tutorial at FCRC [3/9]: VTA

TVM Tutorial at FCRC [3/9]: AutoTVM

TVM Tutorial at FCRC [3/9]: AutoTVM

TVM Tutorial at FCRC [2/9]: Relay

TVM Tutorial at FCRC [2/9]: Relay

TVM Tutorial at FCRC [1/9]: TVM Overview

TVM Tutorial at FCRC [1/9]: TVM Overview

TVM Morning Session #2 (12/12/2018)

TVM Morning Session #2 (12/12/2018)

TVM Afternoon Session #1 (12/12/2018)

TVM Afternoon Session #1 (12/12/2018)

TVM Conference Opening Keynote Session (12/12/18)

TVM Conference Opening Keynote Session (12/12/18)

TVM Morning Session #1 (12/12/2018)

TVM Morning Session #1 (12/12/2018)

TVM Afternoon Session #2 (12/12/2018)

TVM Afternoon Session #2 (12/12/2018)