apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Cherry-Pick][Docs] Update Release Note(#7302) (#7336)

Browse Source
This commit is contained in:
YuBaoku
2026-04-11 16:47:33 +08:00
committed by GitHub
parent 9985b192b4
commit d9d5740c4d
4 changed files with 49 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/get_started/installation/nvidia_gpu.md
+10 -10
View File
@@ -12,10 +12,13 @@ The following installation methods are available when your environment meets the
## 1. Pre-built Docker Installation (Recommended)
**Notice**: The pre-built image supports SM 80/86/89/90 architecture GPUs (e.g. A800/H800/L20/L40/4090).
**Notice**: The pre-built image supports SM 80/86/89/90 architecture GPUs (e.g. A800/H800/L20/L40/4090), and requires Python 3.10.
```shell
# CUDA 12.6
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-cuda-12.6:2.5.0
# CUDA 12.9
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-cuda-12.9:2.5.0
```
## 2. Pre-built Pip Installation
@@ -38,7 +41,7 @@ python -m pip install --pre paddlepaddle-gpu -i https://www.paddlepaddle.org.cn/
Then install fastdeploy. **Do not install from PyPI**. Use the following methods instead (supports SM80/86/89/90 GPU architectures).
**Note**: Stable FastDeploy release pairs with stable PaddlePaddle; Nightly Build FastDeploy pairs with Nightly Build PaddlePaddle. The `--extra-index-url` is only used for downloading fastdeploy-gpu's dependencies; fastdeploy-gpu itself must be installed from the Paddle source specified by `-i`.
```
```shell
# Install stable release FastDeploy
# CUDA 12.6
python -m pip install fastdeploy-gpu==2.5.0 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
@@ -54,7 +57,7 @@ python -m pip install fastdeploy-gpu -i https://www.paddlepaddle.org.cn/packages
## 3. Build from Source Using Docker
- Note: ```dockerfiles/Dockerfile.gpu``` by default supports SM 80/90 architectures. To support other architectures, modify ```bash build.sh 1 python false [80,90]``` in the Dockerfile. It's recommended to specify no more than 2 architectures.
> Note: `dockerfiles/Dockerfile.gpu` currently supports CUDA 12.6 only, targeting SM 80/86/89/90 architectures, and requires Python 3.10. To support other architectures, modify ```bash build.sh 1 python false [80,90]``` in the Dockerfile. It's recommended to specify no more than 2 architectures.
```shell
git clone https://github.com/PaddlePaddle/FastDeploy
@@ -69,8 +72,6 @@ First install paddlepaddle-gpu. For detailed instructions, refer to [PaddlePaddl
```shell
python -m pip install paddlepaddle-gpu==3.3.1 -i https://www.paddlepaddle.org.cn/packages/stable/cu126/
```
Then clone the source code and build:
```shell
git clone https://github.com/PaddlePaddle/FastDeploy
cd FastDeploy
@@ -85,8 +86,7 @@ The built packages will be in the ```FastDeploy/dist``` directory.
## 5. Precompiled Operator Wheel Packages
FastDeploy provides precompiled GPU operator wheel packages for quick setup without building the entire source code.
This method currently supports **SM80/90 architecture (e.g., A100/H100)** and **CUDA 12.6** environments only.
FastDeploy provides precompiled GPU operator wheel packages for quick setup without building the entire source code. This method currently supports **SM80/90 architecture (e.g., A100/H100)** **CUDA 12.6** and **Python 3.10** environments only.
> By default, `build.sh` compiles all custom operators from source.To use the precompiled package, enable it with the `FD_USE_PRECOMPILED` parameter.
> If the precompiled package cannot be downloaded or does not match the current environment, the system will automatically fall back to `4. Build Wheel from Source`.
@@ -115,7 +115,7 @@ cd FastDeploy
bash build.sh 1 python false [90] 1
# Use precompiled wheel from a specific commit
bash build.sh 1 python false [90] 1 8a9e7b53af4a98583cab65e4b44e3265a93e56d2
bash build.sh 1 python false [90] 1 d693d4be1448d414097882386fdc24c8bec2a63a
```
The downloaded wheel packages will be stored in the `FastDeploy/pre_wheel` directory.
@@ -124,9 +124,9 @@ After the build completes, the operator binaries can be found in `FastDeploy/fas
> **Notes:**
>
> - This mode prioritizes downloading precompiled GPU operator wheels to reduce build time.
> - Currently supports **GPU, SM80/90, CUDA 12.6** only.
> - Currently supports **GPU, SM80/90, CUDA 12.6, Python3.10** only.
> - For custom architectures or modified operator logic, please use **source compilation (Section 4)**.
> - You can check whether the precompiled wheel for a specific commit has been successfully built on the [FastDeploy CI Build Status Page](https://github.com/PaddlePaddle/FastDeploy/actions/workflows/ci_image_update.yml).
> - You can check whether the precompiled wheel for a specific commit has been successfully built on the [FastDeploy CI Build Status Page](https://github.com/PaddlePaddle/FastDeploy/actions/workflows/ce_job.yml).
## Environment Verification