---
license: other
license_name: tencent-hunyuan-community
license_link: https://huggingface.co/Tencent-Hunyuan/HunyuanDiT/blob/main/LICENSE.txt
language:
- en
---

# HunyuanDiT TensorRT Acceleration

Language: **English** | [**中文**](https://huggingface.co/Tencent-Hunyuan/TensorRT-libs/blob/main/README_zh.md)

We provide a TensorRT version of [HunyuanDiT](https://github.com/Tencent/HunyuanDiT) for inference acceleration 
(faster than flash attention). One can convert the torch model to TensorRT model using the following steps based on
**TensorRT-9.2.0.5** and **cuda (11.7 or 11.8)**.

> ⚠️ Important Reminder (Suggestion for testing the TensorRT acceleration version):  
> We recommend users to test the TensorRT version on NVIDIA GPUs with Compute Capability >= 8.0,(For example, RTX4090, 
> RTX3090, H800, A10/A100/A800, etc.) you can query the Compute Capability corresponding to your GPU from 
> [here](https://developer.nvidia.com/cuda-gpus#compute). For NVIDIA GPUs with Compute Capability < 8.0, if you want to 
> try the TensorRT version, you may encounter errors that the TensorRT Engine file cannot be generated or the inference 
> performance is poor, the main reason is that TensorRT does not support fused mha kernel on this architecture.

## 🛠 Instructions

### 1. Download dependencies from huggingface.

```shell
cd HunyuanDiT
# Use the huggingface-cli tool to download the model.
huggingface-cli download Tencent-Hunyuan/TensorRT-libs --local-dir ./ckpts/t2i/model_trt
```

### 2. Install the TensorRT dependencies.

```shell
sh trt/install.sh
```

### 3. Build the TensorRT engine.


#### Method 1: Use the prebuilt engine

We provide some prebuilt TensorRT engines. 

|  Supported GPU   |                                                  Download Link                                                  |            Remote Path            |
|:----------------:|:---------------------------------------------------------------------------------------------------------------:|:---------------------------------:|
| GeForce RTX 3090 | [HuggingFace](https://huggingface.co/Tencent-Hunyuan/TensorRT-engine/blob/main/engines/RTX3090/model_onnx.plan) | `engines/RTX3090/model_onnx.plan` |
| GeForce RTX 4090 | [HuggingFace](https://huggingface.co/Tencent-Hunyuan/TensorRT-engine/blob/main/engines/RTX4090/model_onnx.plan) | `engines/RTX4090/model_onnx.plan` |
|       A100       |  [HuggingFace](https://huggingface.co/Tencent-Hunyuan/TensorRT-engine/blob/main/engines/A100/model_onnx.plan)   |  `engines/A100/model_onnx.plan`   |

Use the following command to download and place the engine in the specified location.

```shell
huggingface-cli download Tencent-Hunyuan/TensorRT-engine <Remote Path> --local-dir ./ckpts/t2i/model_trt/engine
```

#### Method 2: Build your own engine

If you are using a different GPU, you can build the engine using the following command.

```shell
# Set the TensorRT build environment variables first. We provide a script to set up the environment.
source trt/activate.sh

# Build the TensorRT engine. By default, it will read the `ckpts` folder in the current directory.
sh trt/build_engine.sh
```

Finally, if you see the output like `&&&& PASSED TensorRT.trtexec [TensorRT v9200]`, the engine is built successfully.

### 4. Run the inference using the TensorRT model.

```shell
# Run the inference using the prompt-enhanced model + HunyuanDiT TensorRT model.
python sample_t2i.py --prompt "渔舟唱晚" --infer-mode trt

# Close prompt enhancement. (save GPU memory)
python sample_t2i.py --prompt "渔舟唱晚" --infer-mode trt --no-enhance
```

## ❓ Q&A

Please refer to the [Q&A](./QA.md) for more questions and answers about building the TensorRT Engine.