Performance Results#
Performance data#
NVIDIA AI for Media Relighting supports concurrent streams per GPU. The number of concurrent streams depends on GPU memory and video resolution.
The following table shows the performance data for Relighting for a single stream on various GPUs with the provided sample input files and the Python client in performance mode.
GPU |
Input Video Resolution |
Average FPS |
|---|---|---|
RTX 5090 |
1080p |
59 |
720p |
32 |
|
4K |
29 |
|
RTX 4090 |
1080p |
53 |
720p |
38 |
|
4K |
28 |
|
RTX Pro 6000 BSE |
1080p |
47 |
720p |
23 |
|
4K |
25 |
|
L40S |
1080p |
43 |
720p |
26 |
|
4K |
25 |
|
A40 |
1080p |
26 |
720p |
16 |
|
4K |
15 |
|
A10G |
1080p |
23 |
720p |
14 |
|
4K |
15 |
|
L4 |
1080p |
21 |
720p |
15 |
|
4K |
14 |
The inference FPS is calculated by dividing the total number of frames in input video file by the total inference time in seconds (measured from the time the request is sent until the complete output file is received by the client).
For more information, refer to the NIM Clients GitHub repository: NVIDIA AI for Media NIM Clients.