Skip to content

Commit 07b21d2

Browse files
qw86972190qw86972190
authored
[XPU]Update documentation (#4917)
* [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
1 parent 5453626 commit 07b21d2

File tree

4 files changed

+174
-23
lines changed

4 files changed

+174
-23
lines changed

‎docs/get_started/installation/kunlunxin_xpu.md‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -27,9 +27,9 @@ Verified platform:
2727
```bash
2828
mkdir Work
2929
cd Work
30-
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0
30+
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0
3131
docker run --name fastdeploy-xpu --net=host -itd --privileged -v $PWD:/Work -w /Work \
32-
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0 \
32+
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0 \
3333
/bin/bash
3434
docker exec -it fastdeploy-xpu /bin/bash
3535
```
@@ -39,7 +39,7 @@ docker exec -it fastdeploy-xpu /bin/bash
3939
### Install PaddlePaddle
4040

4141
```bash
42-
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
42+
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
4343
```
4444

4545
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/
5151
### Install FastDeploy (**Do NOT install via PyPI source**)
5252

5353
```bash
54-
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
54+
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
5555
```
5656

5757
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
6565
### Install PaddlePaddle
6666

6767
```bash
68-
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
68+
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
6969
```
7070

7171
Alternatively, you can install the latest version of PaddlePaddle (Not recommended)

‎docs/usage/kunlunxin_xpu_deployment.md‎

Lines changed: 82 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -6,21 +6,22 @@
66
|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|
77
|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|
88
|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|
9-
|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|
9+
|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|
1010
|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|
1111
|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|
12-
|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|
12+
|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|
1313
|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|
1414
|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|
15-
|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|
15+
|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|
1616
|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|
17-
|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|
17+
|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|
1818
|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|
19-
|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|
19+
|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|
2020
|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|
2121
|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|
2222
|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|
2323
|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|
24+
|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|
2425

2526
## Quick start
2627

@@ -125,7 +126,7 @@ curl -X POST "http://0.0.0.0:8188/v1/chat/completions" \
125126
"messages": [
126127
{"role": "user", "content": [
127128
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
128-
{"type": "text", "text": "请描述图片内容"}
129+
{"type": "text", "text": "Please describe the content of the image"}
129130
]}
130131
],
131132
"metadata": {"enable_thinking": false}
@@ -144,7 +145,7 @@ response = client.chat.completions.create(
144145
messages=[
145146
{"role": "user", "content": [
146147
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
147-
{"type": "text", "text": "请描述图片内容"}
148+
{"type": "text", "text": "Please describe the content of the image"}
148149
]
149150
},
150151
],
@@ -237,3 +238,77 @@ for chunk in response:
237238
print(reasoning_content + content, end='', flush=True)
238239
print('\n')
239240
```
241+
242+
### Deploy online serving based on ERNIE-4.5-VL-28B-A3B-Thinking
243+
244+
#### Start service
245+
Deploy the ERNIE-4.5-VL-28B-A3B-Thinking model with WINT8 precision and 128K context length on 1 XPU
246+
247+
```bash
248+
export XPU_VISIBLE_DEVICES="0"# Specify any card
249+
python -m fastdeploy.entrypoints.openai.api_server \
250+
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Thinking \
251+
--port 8188 \
252+
--tensor-parallel-size 1 \
253+
--quantization "wint8" \
254+
--max-model-len 131072 \
255+
--max-num-seqs 32 \
256+
--engine-worker-queue-port 8189 \
257+
--metrics-port 8190 \
258+
--cache-queue-port 8191 \
259+
--reasoning-parser ernie-45-vl-thinking \
260+
--tool-call-parser ernie-45-vl-thinking \
261+
--mm-processor-kwargs '{"image_max_pixels": 12845056 }'
262+
--load-choices "default_v1"
263+
```
264+
265+
#### Send requests
266+
267+
```bash
268+
curl -X POST "http://0.0.0.0:8188/v1/chat/completions" \
269+
-H "Content-Type: application/json" \
270+
-d '{
271+
"messages": [
272+
{"role": "user", "content": [
273+
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
274+
{"type": "text", "text": "Please describe the content of the image"}
275+
]}
276+
],
277+
"metadata": {"enable_thinking": true}
278+
}'
279+
```
280+
281+
```python
282+
import openai
283+
284+
ip = "0.0.0.0"
285+
service_http_port = "8188"
286+
client = openai.Client(base_url=f"http://{ip}:{service_http_port}/v1", api_key="EMPTY_API_KEY")
287+
288+
response = client.chat.completions.create(
289+
model="default",
290+
messages=[
291+
{"role": "user", "content": [
292+
{"type": "image_url", "image_url": {"url": "https://paddlenlp.bj.bcebos.com/datasets/paddlemix/demo_images/example2.jpg", "detail": "high"}},
293+
{"type": "text", "text": "Please describe the content of the image"}
294+
]
295+
},
296+
],
297+
temperature=0.0001,
298+
max_tokens=10000,
299+
stream=True,
300+
top_p=0,
301+
metadata={"enable_thinking": True},
302+
)
303+
304+
def get_str(content_raw):
305+
content_str = str(content_raw) if content_raw is not None else ''
306+
return content_str
307+
308+
for chunk in response:
309+
if chunk.choices[0].delta is not None and chunk.choices[0].delta.role != 'assistant':
310+
reasoning_content = get_str(chunk.choices[0].delta.reasoning_content)
311+
content = get_str(chunk.choices[0].delta.content)
312+
print(reasoning_content + content + is_reason, end='', flush=True)
313+
print('\n')
314+
```

‎docs/zh/get_started/installation/kunlunxin_xpu.md‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -27,9 +27,9 @@
2727
```bash
2828
mkdir Work
2929
cd Work
30-
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0
30+
docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0
3131
docker run --name fastdeploy-xpu --net=host -itd --privileged -v $PWD:/Work -w /Work \
32-
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0-rc0 \
32+
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.3.0 \
3333
/bin/bash
3434
docker exec -it fastdeploy-xpu /bin/bash
3535
```
@@ -39,7 +39,7 @@ docker exec -it fastdeploy-xpu /bin/bash
3939
### 安装 PaddlePaddle
4040

4141
```bash
42-
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
42+
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
4343
```
4444

4545
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/
5151
### 安装 FastDeploy（**注意不要通过 pypi 源安装**）
5252

5353
```bash
54-
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
54+
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
5555
```
5656

5757
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
6565
### 安装 PaddlePaddle
6666

6767
```bash
68-
python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
68+
python -m pip install paddlepaddle-xpu==3.2.2 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
6969
```
7070

7171
或者您也可以安装最新版 PaddlePaddle（不推荐）

0 commit comments

Comments
 (0)