filmov
tv
Named Tensors, Model Quantization, and the Latest PyTorch Features - Part 1
Показать описание
PyTorch, the popular open-source ML framework, has continued to evolve rapidly since the introduction of PyTorch 1.0, which brought an accelerated workflow from research to production. We'll deep dive on some of the most important new advances, including the ability to name tensors, support for quantization-aware training and post-training quantization, improved distributed training on GPUs, and streamlined mobile deployment. We'll also cover new developer tools and domain-specific frameworks including Captum for model interpretability, Detectron2 for computer vision, and speech extensions for Fairseq.
0:26:36
Named Tensors, Model Quantization, and the Latest PyTorch Features - Part 1
0:15:34
Quantization in deep learning | Deep Learning Tutorial 49 (Tensorflow, Keras & Python)
0:52:51
Deep Dive on PyTorch Quantization - Chris Gottbrath
0:13:04
Quantization in Deep Learning (LLMs)
0:50:55
Quantization explained with PyTorch - Post-Training Quantization, Quantization-Aware Training
0:09:40
Tensors for Neural Networks, Clearly Explained!!!
0:19:46
Quantization vs Pruning vs Distillation: Optimizing NNs for Inference
0:11:30
What’s new in PyTorch 1.3 - Lin Qiao
0:21:21
GTC 2021: Systematic Neural Network Quantization
0:45:36
Tutorial (TVMCon 2021) - Neural Network Quantization with Brevitas
0:42:06
Understanding 4bit Quantization: QLoRA explained (w/ Colab)
0:06:12
Hessian AWare Quantization V3: Dyadic Neural Network Quantization
0:31:26
Understanding Quantization for Deep Learning
0:42:25
Model Quantization for Edge Devices with AIMET
0:04:36
Quantization in PyTorch 2.0 Export at PyTorch Conference 2022
0:09:45
INT8 Inference of Quantization-Aware trained models using ONNX-TensorRT
0:05:35
Tensor Processing Units: History and hardware
0:16:40
Neural Network Compression – Dmitri Puzyrev
0:09:54
Quantization - Dmytro Dzhulgakov
0:06:31
What’s new in TensorFlow 2.11
0:42:35
Inside TensorFlow: TF Model Optimization Toolkit (Quantization and Pruning)
0:40:50
TensorFlow model optimization: Quantization and pruning (TF World '19)
0:01:21
How to Change Data types of Tensors - Tensorflow Basics
0:04:54
Multi-Dimensional Pruning: A Unified Framework for Model Compression
Комментарии