004 ONNX 20211021 Wang ONNX Intel Neural Compressor A Scalable Quantization Tool for ONNX Models

preview_player
Показать описание
LF AI & Data Day - ONNX Community Meeting, October 21, 2021

Intel® Neural Compressor: A Scalable Quantization Tool for ONNX Models

Speaker: Mengni Wang (Intel)
  1. LF AI & Data Foundation
Рекомендации по теме
004 ONNX 20211021 0:07:05

004 ONNX 20211021 Wang ONNX Intel Neural Compressor A Scalable Quantization Tool for ONNX Models

009 ONNX 20211021 0:10:10

009 ONNX 20211021 Knight ONNX TVM for dynamic shapes, control flow, quantization compiler OctoML

005 ONNX 20210324 0:07:11

005 ONNX 20210324 Tom Scott Recording TFLite to ONNX and ORT Mobile

001 ONNX 20210324 0:09:54

001 ONNX 20210324 Welcome Sheng ONNX workshop March 24, 2021

ONNX Roadmap Discussion 0:29:28

ONNX Roadmap Discussion #1 20210908

QONNX: A proposal 0:07:14

QONNX: A proposal for representing arbitrary-precision quantized NNs in ONNX

Fast T5 transformer 0:23:38

Fast T5 transformer model CPU inference with ONNX conversion and quantization

ONNXCommunityMeetup2023: INT8 Quantization 0:08:26

ONNXCommunityMeetup2023: INT8 Quantization for Large Language Models with Intel Neural Compressor

Start Post-Training Static 0:03:59

Start Post-Training Static Quantization | AI Model Optimization with Intel® Neural Compressor

ONNX Roadmap Discussion 0:28:44

ONNX Roadmap Discussion #5 20201001

Intel Innovation 2021 0:03:13

Intel Innovation 2021 Demo: Intel Neural Compressor

Dynamic Quantization with 0:15:20

Dynamic Quantization with Intel Neural Compressor and Transformers

Neural network quantization 0:04:04

Neural network quantization with AdaRound

What is the 0:05:24

What is the Intel oneAPI AI Analytics Toolkit?

Accelerate End-to-End AI 0:03:31

Accelerate End-to-End AI Pipelines Using Intel® AI Analytics Toolkit | Intel Software