Comments (4)
Does Latte support multiple GPUs, and if so, how should it be set up?
Hi, I'm not sure what you mean by multi-GPU? Do you mean multi-GPU training or multi-GPU testing?
from latte.
I followed the steps in the readme to generate videos from text, but only one of my GPUs was used.
(base) root@nvidia3090:/home/nvidia3090# nvidia-smi
Sat Feb 24 07:13:27 2024
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.154.05 Driver Version: 535.154.05 CUDA Version: 12.2 |
|-----------------------------------------+----------------------+----------------------+
| 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 RTX 3090 Off | 00000000:04:00.0 Off | N/A |
| 0% 24C P2 349W / 350W | 21275MiB / 24576MiB | 100% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce RTX 3090 Off | 00000000:06:00.0 Off | N/A |
| 0% 5C P8 28W / 350W | 2788MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 2 NVIDIA GeForce RTX 3090 Off | 00000000:07:00.0 Off | N/A |
| 0% 5C P8 24W / 350W | 2770MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 3 NVIDIA GeForce RTX 3090 Off | 00000000:0C:00.0 Off | N/A |
| 0% 5C P8 20W / 370W | 2786MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 4 NVIDIA GeForce RTX 3090 Off | 00000000:0D:00.0 Off | N/A |
| 0% 4C P8 20W / 350W | 2776MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
| 5 NVIDIA GeForce RTX 3090 Off | 00000000:0E:00.0 Off | N/A |
| 0% 4C P8 24W / 420W | 2786MiB / 24576MiB | 0% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 1210829 C python 2810MiB |
| 0 N/A N/A 1355236 C python 18456MiB |
| 1 N/A N/A 1210766 C python 2782MiB |
| 2 N/A N/A 1210696 C python 2764MiB |
| 3 N/A N/A 1210629 C python 2780MiB |
| 4 N/A N/A 1210479 C python 2770MiB |
| 5 N/A N/A 1210343 C python 2780MiB |
+---------------------------------------------------------------------------------------+
from latte.
I followed the steps in the readme to generate videos from text, but only one of my GPUs was used. (base) root@nvidia3090:/home/nvidia3090# nvidia-smi Sat Feb 24 07:13:27 2024 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.154.05 Driver Version: 535.154.05 CUDA Version: 12.2 | |-----------------------------------------+----------------------+----------------------+ | 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 RTX 3090 Off | 00000000:04:00.0 Off | N/A | | 0% 24C P2 349W / 350W | 21275MiB / 24576MiB | 100% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ | 1 NVIDIA GeForce RTX 3090 Off | 00000000:06:00.0 Off | N/A | | 0% 5C P8 28W / 350W | 2788MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ | 2 NVIDIA GeForce RTX 3090 Off | 00000000:07:00.0 Off | N/A | | 0% 5C P8 24W / 350W | 2770MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ | 3 NVIDIA GeForce RTX 3090 Off | 00000000:0C:00.0 Off | N/A | | 0% 5C P8 20W / 370W | 2786MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ | 4 NVIDIA GeForce RTX 3090 Off | 00000000:0D:00.0 Off | N/A | | 0% 4C P8 20W / 350W | 2776MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ | 5 NVIDIA GeForce RTX 3090 Off | 00000000:0E:00.0 Off | N/A | | 0% 4C P8 24W / 420W | 2786MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 1210829 C python 2810MiB | | 0 N/A N/A 1355236 C python 18456MiB | | 1 N/A N/A 1210766 C python 2782MiB | | 2 N/A N/A 1210696 C python 2764MiB | | 3 N/A N/A 1210629 C python 2780MiB | | 4 N/A N/A 1210479 C python 2770MiB | | 5 N/A N/A 1210343 C python 2780MiB | +---------------------------------------------------------------------------------------+
The code that generates videos from texts does not currently support the multi-GPU parallel mode. If you want to generate video on multiple Gpus, please refer to sample_ddp.py to modify your code.
from latte.
Thanks for your answer
from latte.
Related Issues (20)
- Is autoregression possible? HOT 3
- Questions about the *0.18215 and /0.18215 operation HOT 2
- About video VAE HOT 1
- 有关时长的问题。 HOT 3
- question on t2v model training HOT 1
- 视频帧率 HOT 1
- Question: model code and design choices HOT 1
- how to place and preprocess these datasets HOT 6
- the code of variant 4 HOT 1
- Question: evaluate the FVD HOT 6
- Error once speed up training HOT 2
- How to get preprocessed_ffs HOT 3
- Any plan to implement Latte in HuggingFace's diffusers library? HOT 3
- 模型在ucf101上无法收敛 HOT 5
- Can Latte train for I2V tasks? HOT 2
- Batch Size Ablations HOT 1
- what the param <input_sq_size> stands for? HOT 2
- Can we use batch_size>1 in sample_t2x.py HOT 7
- Evaluate the `FVD` on FFS HOT 4
- How can I utilize the weights of pre-trained PixArt-α to initialize the parameters of the spatial Transformer block in the Latte T2V model? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from latte.