Support Matrix#

Sequence Databases and Search Types#

The MSA NIM supports a variety of MMSeqs2-compatible databases (both those prepared by the user and pre-made indexes available as NGC Models). The following databases are currently available on NGC:

NGC Model Name

Databases Supported

Search Types Supported

Size (GB)

Source

0.1.8-colabfold

Uniref30_2302, colabfold_envdb_202108, and PDB70_220313

alphafold2 and colabfold

1200

ColabFold Databases

0.1.8-alphafold

uniref90, small_bfd, and mgnify

alphafold2

520

AlphaFold2 Databases

Supported Hardware#

Minimum System Hardware Requirements#

CPU Cores

RAM (GB)

NVMe SSD Storage (GB)

GPU Count

24

64

1300

One or More NVIDIA GPU from the list of Supported NVIDIA GPUs

Supported NVIDIA GPUs#

The MSA Search NIM supports NVIDIA GPUs with at least 48 GB of GPU Memory. It has been tested on the following recommended configurations:

GPU

GPU Memory (GB)

GPU Count

A100

80

1-8

H100

80

1-8

L40s

48

1-8

RTX 6000 Ada Generation (beta)

48

1-4

Testing Locally Available Hardware#

docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi

Example output:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 525.78.01    Driver Version: 525.78.01    CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  Off  | 00000000:01:00.0 Off |                  N/A |
| 41%   30C    P8     1W / 260W |   2244MiB / 11264MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
+-----------------------------------------------------------------------------+

Note

For more information on enumerating multi-GPU systems, refer to the NVIDIA Container Toolkit’s GPU Enumeration Docs

On this page