apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[XPU]Update documentation (#4917)

Browse Source 
* [XPU]Update documentation

* [XPU]Update documentation

* [XPU]Update documentation

* [XPU]Update documentation

* [XPU][Docs] Update documentation

* [XPU][Docs] Update documentation

* [XPU][Docs] Update documentation

* [XPU][Docs] Update documentation

* [XPU][Docs] Update documentation

* [XPU][Docs] Update documentation
This commit is contained in:
qw86972190
2025-11-10 19:11:42 +08:00
committed by GitHub
parent 54536267db
commit 07b21d241d
4 changed files with 174 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/get_started/installation/kunlunxin_xpu.md
View File

@@ -27,9 +27,9 @@ Verified platform:
```bash
mkdir Work
cd Work
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0
docker run --name fastdeploy-xpu --net=host -itd --privileged -v $PWD:/Work -w /Work \
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0 \
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0 \
/bin/bash
docker exec -it fastdeploy-xpu /bin/bash
```
@@ -39,7 +39,7 @@ docker exec -it fastdeploy-xpu /bin/bash
### Install PaddlePaddle
```bash
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
```
Alternatively, you can install the latest version of PaddlePaddle (Not recommended)
@@ -51,7 +51,7 @@ python -m pip install --pre paddlepaddle-xpu -i https://www.paddlepaddle.org.cn/
### Install FastDeploy (**Do NOT install via PyPI source**)
```bash
python -m pip install fastdeploy-xpu==2.3.0-rc0 -i https://www.paddlepaddle.org.cn/packages/stable/fastdeploy-xpu-p800/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
python -m pip install fastdeploy-xpu==2.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/fastdeploy-xpu-p800/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
```
Alternatively, you can install the latest version of FastDeploy (Not recommended)
@@ -65,7 +65,7 @@ python -m pip install --pre fastdeploy-xpu -i https://www.paddlepaddle.org.cn/pa
### Install PaddlePaddle
```bash
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
```
Alternatively, you can install the latest version of PaddlePaddle (Not recommended)

89
docs/usage/kunlunxin_xpu_deployment.md
View File

@@ -6,21 +6,22 @@
|ERNIE-4.5-300B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|32K|WINT4|4 (Recommended)|export XPU_VISIBLE_DEVICES="0,1,2,3" or "4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 4 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|32K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.95 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|128K|WINT4|8 (Recommended)|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|128K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|WINT4|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|WINT4|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|32K|WINT8|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|128K|WINT8|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B-W4A8C8-TP4|32K|W4A8|4|export XPU_VISIBLE_DEVICES="0,1,2,3" or "4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 4 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "W4A8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-VL-28B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --quantization "wint8" \ <br> --max-model-len 32768 \ <br> --max-num-seqs 10 \ <br> --enable-mm \ <br> --mm-processor-kwargs '{"video_max_frames": 30}' \ <br> --limit-mm-per-prompt '{"image": 10, "video": 3}' \ <br> --reasoning-parser ernie-45-vl \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-VL-424B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" <br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-VL-424B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --quantization "wint8" \ <br> --max-model-len 32768 \ <br> --max-num-seqs 8 \ <br> --enable-mm \ <br> --mm-processor-kwargs '{"video_max_frames": 30}' \ <br> --limit-mm-per-prompt '{"image": 10, "video": 3}' \ <br> --reasoning-parser ernie-45-vl \ <br> --load-choices "default"|2.3.0|
|PaddleOCR-VL-0.9B|32K|BF16|1|export FD_ENABLE_MAX_PREFILL=1 <br>export XPU_VISIBLE_DEVICES="0" # Specify any card <br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/PaddleOCR-VL \ <br> --port 8188 \ <br> --metrics-port 8181 \ <br> --engine-worker-queue-port 8182 \ <br> --max-model-len 16384 \ <br> --max-num-batched-tokens 16384 \ <br> --gpu-memory-utilization 0.8 \ <br> --max-num-seqs 256|2.3.0|
|ERNIE-4.5-VL-28B-A3B-Thinking|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0"# Specify any card<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Thinking \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --quantization "wint8" \ <br> --max-model-len 131072 \ <br> --max-num-seqs 32 \ <br> --engine-worker-queue-port 8189 \ <br> --metrics-port 8190 \ <br> --cache-queue-port 8191 \ <br> --reasoning-parser ernie-45-vl-thinking \ <br> --tool-call-parser ernie-45-vl-thinking \ <br> --mm-processor-kwargs '{"image_max_pixels": 12845056 }' <br> --load-choices "default_v1"|2.3.0|
## Quick start
@@ -125,7 +126,7 @@ curl -X POST "http://0.0.0.0:8188/v1/chat/completions" \
"messages": [
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
{"type": "text", "text": "请描述图片内容"}
{"type": "text", "text": "Please describe the content of the image"}
]}
],
"metadata": {"enable_thinking": false}
@@ -144,7 +145,7 @@ response = client.chat.completions.create(
messages=[
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
{"type": "text", "text": "请描述图片内容"}
{"type": "text", "text": "Please describe the content of the image"}
]
},
],
@@ -237,3 +238,77 @@ for chunk in response:
print(reasoning_content + content, end='', flush=True)
print('\n')
```
### Deploy online serving based on ERNIE-4.5-VL-28B-A3B-Thinking
#### Start service
Deploy the ERNIE-4.5-VL-28B-A3B-Thinking model with WINT8 precision and 128K context length on 1 XPU
```bash
export XPU_VISIBLE_DEVICES="0"# Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Thinking \
--port 8188 \
--tensor-parallel-size 1 \
--quantization "wint8" \
--max-model-len 131072 \
--max-num-seqs 32 \
--engine-worker-queue-port 8189 \
--metrics-port 8190 \
--cache-queue-port 8191 \
--reasoning-parser ernie-45-vl-thinking \
--tool-call-parser ernie-45-vl-thinking \
--mm-processor-kwargs '{"image_max_pixels": 12845056 }'
--load-choices "default_v1"
```
#### Send requests
```bash
curl -X POST "http://0.0.0.0:8188/v1/chat/completions" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
{"type": "text", "text": "Please describe the content of the image"}
]}
],
"metadata": {"enable_thinking": true}
}'
```
```python
import openai
ip = "0.0.0.0"
service_http_port = "8188"
client = openai.Client(base_url=f"http://{ip}:{service_http_port}/v1", api_key="EMPTY_API_KEY")
response = client.chat.completions.create(
model="default",
messages=[
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
{"type": "text", "text": "Please describe the content of the image"}
]
},
],
temperature=0.0001,
max_tokens=10000,
stream=True,
top_p=0,
metadata={"enable_thinking": True},
)
def get_str(content_raw):
content_str = str(content_raw) if content_raw is not None else ''
return content_str
for chunk in response:
if chunk.choices[0].delta is not None and chunk.choices[0].delta.role != 'assistant':
reasoning_content = get_str(chunk.choices[0].delta.reasoning_content)
content = get_str(chunk.choices[0].delta.content)
print(reasoning_content + content + is_reason, end='', flush=True)
print('\n')
```

10
docs/zh/get_started/installation/kunlunxin_xpu.md
View File

@@ -27,9 +27,9 @@
```bash
mkdir Work
cd Work
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0
docker run --name fastdeploy-xpu --net=host -itd --privileged -v $PWD:/Work -w /Work \
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0 \
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0 \
/bin/bash
docker exec -it fastdeploy-xpu /bin/bash
```
@@ -39,7 +39,7 @@ docker exec -it fastdeploy-xpu /bin/bash
### 安装 PaddlePaddle
```bash
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
```
或者您也可以安装最新版 PaddlePaddle（不推荐）
@@ -51,7 +51,7 @@ python -m pip install --pre paddlepaddle-xpu -i https://www.paddlepaddle.org.cn/
### 安装 FastDeploy（**注意不要通过 pypi 源安装**）
```bash
python -m pip install fastdeploy-xpu==2.3.0-rc0 -i https://www.paddlepaddle.org.cn/packages/stable/fastdeploy-xpu-p800/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
python -m pip install fastdeploy-xpu==2.3.0 -i https://www.paddlepaddle.org.cn/packages/stable/fastdeploy-xpu-p800/ --extra-index-url https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
```
或者你也可以安装最新版 FastDeploy（不推荐）
@@ -65,7 +65,7 @@ python -m pip install --pre fastdeploy-xpu -i https://www.paddlepaddle.org.cn/pa
### 安装 PaddlePaddle
```bash
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
```
或者您也可以安装最新版 PaddlePaddle（不推荐）

88
docs/zh/usage/kunlunxin_xpu_deployment.md
View File

@@ -6,21 +6,22 @@
|ERNIE-4.5-300B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|32K|WINT4|4 （推荐）|export XPU_VISIBLE_DEVICES="0,1,2,3" or "4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 4 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|32K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.95 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|128K|WINT4|8 （推荐）|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B|128K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 64 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|32K|WINT4|1 （推荐）|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-21B-A3B|128K|WINT4|1 （推荐）|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint4" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="x" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|32K|WINT8|1 （推荐）|export XPU_VISIBLE_DEVICES="x" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-0.3B|128K|WINT8|1 （推荐）|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --max-model-len 131072 \ <br> --max-num-seqs 128 \ <br> --quantization "wint8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-300B-A47B-W4A8C8-TP4|32K|W4A8|4|export XPU_VISIBLE_DEVICES="0,1,2,3" or "4,5,6,7"<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 4 \ <br> --max-model-len 32768 \ <br> --max-num-seqs 64 \ <br> --quantization "W4A8" \ <br> --gpu-memory-utilization 0.9 \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-VL-28B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0"# 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --quantization "wint8" \ <br> --max-model-len 32768 \ <br> --max-num-seqs 10 \ <br> --enable-mm \ <br> --mm-processor-kwargs '{"video_max_frames": 30}' \ <br> --limit-mm-per-prompt '{"image": 10, "video": 3}' \ <br> --reasoning-parser ernie-45-vl \ <br> --load-choices "default"|2.3.0|
|ERNIE-4.5-VL-424B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" <br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-VL-424B-A47B-Paddle \ <br> --port 8188 \ <br> --tensor-parallel-size 8 \ <br> --quantization "wint8" \ <br> --max-model-len 32768 \ <br> --max-num-seqs 8 \ <br> --enable-mm \ <br> --mm-processor-kwargs '{"video_max_frames": 30}' \ <br> --limit-mm-per-prompt '{"image": 10, "video": 3}' \ <br> --reasoning-parser ernie-45-vl \ <br> --load-choices "default"|2.3.0|
|PaddleOCR-VL-0.9B|32K|BF16|1|export FD_ENABLE_MAX_PREFILL=1 <br>export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡 <br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/PaddleOCR-VL \ <br> --port 8188 \ <br> --metrics-port 8181 \ <br> --engine-worker-queue-port 8182 \ <br> --max-model-len 16384 \ <br> --max-num-batched-tokens 16384 \ <br> --gpu-memory-utilization 0.8 \ <br> --max-num-seqs 256|2.3.0|
|ERNIE-4.5-VL-28B-A3B-Thinking|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0"# 指定任意一张卡<br>python -m fastdeploy.entrypoints.openai.api_server \ <br> --model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Thinking \ <br> --port 8188 \ <br> --tensor-parallel-size 1 \ <br> --quantization "wint8" \ <br> --max-model-len 131072 \ <br> --max-num-seqs 32 \ <br> --engine-worker-queue-port 8189 \ <br> --metrics-port 8190 \ <br> --cache-queue-port 8191 \ <br> --reasoning-parser ernie-45-vl-thinking \ <br> --tool-call-parser ernie-45-vl-thinking \ <br> --mm-processor-kwargs '{"image_max_pixels": 12845056 }' <br> --load-choices "default_v1"|2.3.0|
## 快速开始
@@ -103,7 +104,7 @@ OpenAI 协议的更多说明可参考文档 [OpenAI Chat Completion API](https:/
基于 WINT8 精度和 32K 上下文部署 ERNIE-4.5-VL-28B-A3B-Paddle 模型到 单卡 P800 服务器
```bash
export XPU_VISIBLE_DEVICES="0" # Specify any card
export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Paddle \
--port 8188 \
@@ -239,3 +240,78 @@ for chunk in response:
print(reasoning_content + content, end='', flush=True)
print('\n')
```
### 基于ERNIE-4.5-VL-28B-A3B-Thinking模型部署在线服务
#### 启动服务
基于 WINT8 精度和 128K 上下文部署 ERNIE-4.5-VL-28B-A3B-Thinking 模型到 单卡 P800 服务器
```bash
export XPU_VISIBLE_DEVICES="0"# 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Thinking \
--port 8188 \
--tensor-parallel-size 1 \
--quantization "wint8" \
--max-model-len 131072 \
--max-num-seqs 32 \
--engine-worker-queue-port 8189 \
--metrics-port 8190 \
--cache-queue-port 8191 \
--reasoning-parser ernie-45-vl-thinking \
--tool-call-parser ernie-45-vl-thinking \
--mm-processor-kwargs '{"image_max_pixels": 12845056 }'
--load-choices "default_v1"
```
#### 请求服务
```bash
curl -X POST "http://0.0.0.0:8188/v1/chat/completions" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
{"type": "text", "text": "请描述图片内容"}
]}
],
"metadata": {"enable_thinking": true}
}'
```
```python
import openai
ip = "0.0.0.0"
service_http_port = "8188"
client = openai.Client(base_url=f"http://{ip}:{service_http_port}/v1", api_key="EMPTY_API_KEY")
response = client.chat.completions.create(
model="default",
messages=[
{"role": "user", "content": [
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
{"type": "text", "text": "请描述图片内容"}
]
},
],
temperature=0.0001,
max_tokens=10000,
stream=True,
top_p=0,
metadata={"enable_thinking": True},
)
def get_str(content_raw):
content_str = str(content_raw) if content_raw is not None else ''
return content_str
for chunk in response:
if chunk.choices[0].delta is not None and chunk.choices[0].delta.role != 'assistant':
reasoning_content = get_str(chunk.choices[0].delta.reasoning_content)
content = get_str(chunk.choices[0].delta.content)
print(reasoning_content + content, end='', flush=True)
print('\n')
```