[Docs]Update XPU document version to 2.3.0 (#4741)

* [Doc]Update XPU document version to 2.3.0 * update paddle doc version * update applicable version
2025-12-24 13:28:13 +08:00 · 2025-11-03 09:54:51 +08:00
parent 9eff788658
commit b8bf57138f
4 changed files with 46 additions and 46 deletions
--- a/docs/get_started/installation/kunlunxin_xpu.md
+++ b/docs/get_started/installation/kunlunxin_xpu.md
@@ -27,9 +27,9 @@ Verified platform:
 ```bash
 mkdir Work
 cd Work
-docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.2.1
+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:2.2.1 \
+    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==3.2.0 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
+python -m pip install paddlepaddle-xpu==3.2.1 -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==2.2.1 -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==3.2.0 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
+python -m pip install paddlepaddle-xpu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
 ```

 Alternatively, you can install the latest version of PaddlePaddle (Not recommended)
--- a/docs/usage/kunlunxin_xpu_deployment.md
+++ b/docs/usage/kunlunxin_xpu_deployment.md
@@ -1,24 +1,25 @@
 [简体中文](../zh/usage/kunlunxin_xpu_deployment.md)

 ## Supported Models
-|Model Name|Context Length|Quantization|XPUs Required|Deployment Commands|Minimum Version Required|
+|Model Name|Context Length|Quantization|XPUs Required|Deployment Commands|Applicable Version|
 |-|-|-|-|-|-|
-|ERNIE-4.5-300B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.3|
-|ERNIE-4.5-300B-A47B|32K|WINT4|4 (Recommended)|export XPU_VISIBLE_DEVICES="0,1,2,3" or "4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.0|
-|ERNIE-4.5-300B-A47B|32K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.0|
-|ERNIE-4.5-300B-A47B|128K|WINT4|8 (Recommended)|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.0|
-|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|32K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|128K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.1.0|
-|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.3|
-|ERNIE-4.5-0.3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.3|
-|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.3|
-|ERNIE-4.5-0.3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported<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"|>=2.0.3|
-|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 |>=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 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 |>=2.3.0|
+|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-4.5-21B-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|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-4.5-0.3B|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|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-4.5-300B-A47B-W4A8C8-TP4-Paddle|64K|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 |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 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 |2.3.0|

 ## Quick start

@@ -30,7 +31,6 @@ Deploy the ERNIE-4.5-300B-A47B-Paddle model with WINT4 precision and 32K context

 ```bash
 export XPU_VISIBLE_DEVICES="0,1,2,3" # Specify which cards to be used
-export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1 is not supported
 python -m fastdeploy.entrypoints.openai.api_server \
    --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
    --port 8188 \
--- a/docs/zh/get_started/installation/kunlunxin_xpu.md
+++ b/docs/zh/get_started/installation/kunlunxin_xpu.md
@@ -27,9 +27,9 @@
 ```bash
 mkdir Work
 cd Work
-docker pull ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/fastdeploy-xpu:2.2.1
+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:2.2.1 \
+    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==3.2.0 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
+python -m pip install paddlepaddle-xpu==3.2.1 -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==2.2.1 -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==3.2.0 -i https://www.paddlepaddle.org.cn/packages/stable/xpu-p800/
+python -m pip install paddlepaddle-xpu==3.2.1 -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）
--- a/docs/zh/usage/kunlunxin_xpu_deployment.md
+++ b/docs/zh/usage/kunlunxin_xpu_deployment.md
@@ -1,24 +1,25 @@
 [English](../../usage/kunlunxin_xpu_deployment.md)

 ## 支持的模型
-|模型名|上下文长度|量化|所需卡数|部署命令|最低版本要求|
+|模型名|上下文长度|量化|所需卡数|部署命令|适用版本|
 |-|-|-|-|-|-|
-|ERNIE-4.5-300B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.3|
-|ERNIE-4.5-300B-A47B|32K|WINT4|4 （推荐）|export XPU_VISIBLE_DEVICES="0,1,2,3" or "4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.0|
-|ERNIE-4.5-300B-A47B|32K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.0|
-|ERNIE-4.5-300B-A47B|128K|WINT4|8 （推荐）|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.0|
-|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|32K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.1.0|
-|ERNIE-4.5-21B-A3B|128K|WINT4|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.1.0|
-|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.3|
-|ERNIE-4.5-0.3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="x" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.3|
-|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.3|
-|ERNIE-4.5-0.3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡<br>export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持<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"|>=2.0.3|
-|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 |>=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 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 |>=2.3.0|
+|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-4.5-21B-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|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-4.5-0.3B|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|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-4.5-300B-A47B-W4A8C8-TP4-Paddle|64K|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 |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 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 |2.3.0|

 ## 快速开始

@@ -30,7 +31,6 @@

 ```bash
 export XPU_VISIBLE_DEVICES="0,1,2,3" # 设置使用的 XPU 卡
-export ENABLE_V1_KVCACHE_SCHEDULER=0 # V1不支持
 python -m fastdeploy.entrypoints.openai.api_server \
    --model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
    --port 8188 \