Skip to content

Latest commit

 

History

History
80 lines (60 loc) · 3.4 KB

CONTAINER_FLEX.md

File metadata and controls

80 lines (60 loc) · 3.4 KB
Raw

Running DistilBERT inference on Intel® Data Center GPU Flex Series using Intel® Extension for PyTorch*

Overview

This document has instructions for running DistilBERT inference inference using Intel® Extension for PyTorch on Intel® Flex Series GPU.

Requirements

Item Detail
Host machine Intel® Data Center GPU Flex Series 170
Drivers GPU-compatible drivers need to be installed: Download Driver
Software Docker*

Datasets

Refer to instructions here to download and prepare the dataset. Set DATASET_DIR to point to the dataset directory.

Quick Start Scripts

Script name Description
run_model.sh Inference with batch size 32 on Flex series 170

Run Using Docker

Set up Docker Image

docker pull intel/language-modeling:pytorch-flex-gpu-distilbert-inference

Run Docker Image

The distilbert inference container includes scripts, model and libraries needed to run FP16 and FP32 inference. To run the run_model.sh quickstart script using this container, you will need to provide an output directory where log files will be written.

#Optional 
export PRECISION=<provide FP32 or FP16 otherwise (default:FP16)>
export BATCH_SIZE=<provide batch size otherwise (default:32)>
export NUM_ITERATIONS=<provide num_iterations otherwise (default:300)>

#Required
export PLATFORM=Flex
export MULTI_TILE=False
export OUTPUT_DIR=<path to output directory>
export SCRIPT=run_model.sh
export DATASET_DIR=<path to dataset directory>

IMAGE=intel/language-modeling:pytorch-flex-gpu-distilbert-inference
DOCKER_ARGS="--rm -it"

docker run \
  --privileged \
  --device=/dev/dri \
  --ipc=host \
  --env PRECISION=${PRECISION} \
  --env DATASET_DIR=${DATASET_DIR} \
  --env NUM_ITERATIONS=${NUM_ITERATIONS} \
  --env OUTPUT_DIR=${OUTPUT_DIR} \
  --env MULTI_TILE=${MULTI_TILE} \
  --env PLATFORM=${PLATFORM} \
  --env http_proxy=${http_proxy} \
  --env https_proxy=${https_proxy} \
  --env no_proxy=${no_proxy} \
  --volume ${OUTPUT_DIR}:${OUTPUT_DIR} \
  --volume ${DATASET_DIR}:${DATASET_DIR} \
  ${DOCKER_ARGS} \
  ${IMAGE_NAME} \
  /bin/bash $SCRIPT

Documentation and Sources

GitHub* Repository

Support

Support for Intel® Extension for PyTorch* is found via the Intel® AI Analytics Toolkit. Additionally, the Intel® Extension for PyTorch* team tracks both bugs and enhancement requests using GitHub issues. Before submitting a suggestion or bug report, please search the GitHub issues to see if your issue has already been reported.

License Agreement

LEGAL NOTICE: By accessing, downloading or using this software and any required dependent software (the “Software Package”), you agree to the terms and conditions of the software license agreements for the Software Package, which may also include notices, disclaimers, or license terms for third party software included with the Software Package. Please refer to the license file for additional details.