Upload ./README.md with huggingface_hub

README.md

@@ -8,12 +8,22 @@ language:
 
 # HunyuanDiT TensorRT Acceleration
 
-English | [中文](https://huggingface.co/Tencent-Hunyuan/TensorRT-libs/blob/main/README_zh.md)
+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.
+(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)**.
 
-## 1. Download dependencies from huggingface.
+> ⚠️ 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
@@ -21,16 +31,16 @@ cd HunyuanDiT
 huggingface-cli download Tencent-Hunyuan/TensorRT-libs --local-dir ./ckpts/t2i/model_trt
 ```
 
-## 2. Install the TensorRT dependencies.
+### 2. Install the TensorRT dependencies.
 
 ```shell
 sh trt/install.sh
 ```
 
-## 3. Build the TensorRT engine.
+### 3. Build the TensorRT engine.
 
 
-### Method 1: Use the prebuilt engine
+#### Method 1: Use the prebuilt engine
 
 We provide some prebuilt TensorRT engines. 
 
@@ -46,7 +56,7 @@ Use the following command to download and place the engine in the specified loca
 huggingface-cli download Tencent-Hunyuan/TensorRT-engine <Remote Path> --local-dir ./ckpts/t2i/model_trt/engine
 ```
 
-### Method 2: Build your own engine
+#### Method 2: Build your own engine
 
 If you are using a different GPU, you can build the engine using the following command.
 
@@ -54,14 +64,13 @@ If you are using a different GPU, you can build the engine using the following c
 # Set the TensorRT build environment variables first. We provide a script to set up the environment.
 source trt/activate.sh
 
-# Method 1: Build the TensorRT engine. By default, it will read the `ckpts` folder in the current directory.
+# Build the TensorRT engine. By default, it will read the `ckpts` folder in the current directory.
 sh trt/build_engine.sh
-
-# Method 2: If your model directory is not `ckpts`, you need to specify the model directory.
-sh trt/build_engine.sh </path/to/ckpts>
 ```
 
-4. Run the inference using the TensorRT model.
+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.
@@ -71,3 +80,7 @@ python sample_t2i.py --prompt "渔舟唱晚" --infer-mode trt
 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.
+