Merlin TensorFlow Training Support Matrix

This container enables you to perform preprocessing and feature engineering with NVTabular so that you can train a deep learning recommendation model with TensorFlow.

22.xx Container Images

Container Release

Release 22.04

Release 22.03

Release 22.02

Release 22.01

DGX

DGX System

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

Operating System

Ubuntu 20.04.4 LTS

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

NVIDIA Certified Systems

NVIDIA Driver

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

GPU Model

Base Container Image

Container Operating System

Ubuntu 20.04.4 LTS

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

Base Container

nvcr.io/nvidia/tensorflow:22.03-tf2-py3

nvcr.io/nvidia/tensorflow:22.02-tf2-py3

nvcr.io/nvidia/tensorflow:22.01-tf2-py3

nvcr.io/nvidia/tensorflow:21.12-tf2-py3

CUDA

11.6.1.005

11.6.0.021

11.6.0.020

11.5.0.029

RMM

22.2.0a0+37.gf2b1364

21.12.00a+31.g0acbd51

21.12.00a+31.g0acbd51

0+untagged.1.gae27a57

cuDF

22.2.0a0+309.gdad51a548e

21.12.00a+293.g0930f712e6

21.12.00a+293.g0930f712e6

0+untagged.1.ge05bd4b

cuDNN

8.3.3.40+cuda11.5

8.3.2.44+cuda11.5

8.3.2.44+cuda11.5

8.3.1.22

Merlin Core

0.2.0

v0.1.1+3.gee1d59d

Not applicable

Not applicable

Merlin Models

0.3.0

Not applicable

Not applicable

Not applicable

Merlin Systems

0.1.0

Not applicable

Not applicable

Not applicable

NVTabular

1.0.0

0.11.0

0.10.0

0.9.0+1.g31f9350

Transformers4Rec

0.1.7

0.1.6

0.1.4

0.1.4

HugeCTR

Not applicable

Not applicable

Not applicable

Not applicable

SM

Not applicable

Not applicable

Not applicable

Not applicable

TensorFlow

2.8.0+nv21.12

2.7.0

2.7.0

2.6.2

Size

13.34 GB

12.68 GB

13.37 GB

13.66 GB

21.xx Container Images

Container Release

Release 21.12

Release 21.11

Release 21.09

DGX

DGX System

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

  • DGX-1

  • DGX-2

  • DGX A100

  • DGX Station

Operating System

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

NVIDIA Certified Systems

NVIDIA Driver

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

NVIDIA Driver version 465.19.01

or later is required. However,

if you’re running on Data Center

GPUs (formerly Tesla) such as T4,

you can use any of the following

NVIDIA Driver versions:

  • 418.40 (or later R418)

  • 440.33 (or later R440)

  • 450.51 (or later R450)

  • 460.27 (or later R460)

Note: The CUDA Driver

Compatibility Package does not

support all drivers.

GPU Model

Base Container Image

Container Operating System

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

Ubuntu 20.04.3 LTS

Base Container

nvcr.io/nvidia/tensorflow:21.11-tf2-py3

nvcr.io/nvidia/tensorflow:21.10-tf2-py3

nvcr.io/nvidia/tensorflow:21.07-tf2-py3

CUDA

11.5.0.029

11.4.3.001

11.4.0.031

RMM

0+untagged.1.gccd9647

0+unknown

0+unknown

cuDF

0+untagged.1.g0a00579

21.08.03

21.08.02

cuDNN

8.3.0.96

8.2.4.15

8.2.2.26

Merlin Core

Not applicable

Not applicable

Not applicable

Merlin Models

Not applicable

Not applicable

Not applicable

Merlin Systems

Not applicable

Not applicable

Not applicable

NVTabular

0.8.0

0.7.1

0.7.0

Transformers4Rec

0.1.3

0.1.2

0.1.1

HugeCTR

Not applicable

Not applicable

Not applicable

SM

Not applicable

Not applicable

Not applicable

TensorFlow

2.6.0

2.6.1

2.5.0

Size

13.05 GB

13.38 GB

13.85 GB