diff --git a/docs/usage/kunlunxin_xpu_deployment.md b/docs/usage/kunlunxin_xpu_deployment.md
index ae101673c..16b064620 100644
--- a/docs/usage/kunlunxin_xpu_deployment.md
+++ b/docs/usage/kunlunxin_xpu_deployment.md
@@ -3,25 +3,25 @@
## Supported Models
|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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.95 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 131072 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-21B-A3B|32K|WINT4|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-21B-A3B|128K|WINT4|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-0.3B|32K|WINT8|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-0.3B|128K|WINT8|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "W4A8" \
--gpu-memory-utilization 0.9 \
--load-choices "default"|2.3.0|
-|ERNIE-4.5-VL-28B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 10 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-424B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 8 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--gpu-memory-utilization 0.7 \
--load-choices "default"|2.3.0|
+|ERNIE-4.5-300B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-300B-A47B|32K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.95|2.3.0|
+|ERNIE-4.5-300B-A47B|128K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 131072 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 |2.3.0|
+|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|32K|WINT4|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 |2.3.0|
+|ERNIE-4.5-21B-A3B|128K|WINT4|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-0.3B|32K|WINT8|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-0.3B|128K|WINT8|1 (Recommended)|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "W4A8" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-VL-28B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 10 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-424B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 8 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--gpu-memory-utilization 0.7|2.3.0|
|PaddleOCR-VL-0.9B|32K|BF16|1|export FD_ENABLE_MAX_PREFILL=1
export XPU_VISIBLE_DEVICES="0" # Specify any card
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/PaddleOCR-VL \
--port 8188 \
--metrics-port 8181 \
--engine-worker-queue-port 8182 \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--gpu-memory-utilization 0.8 \
--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
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"|2.3.0|
+|ERNIE-4.5-VL-28B-A3B-Thinking|128K|WINT8|1|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 }'|2.3.0|
## Quick start
diff --git a/docs/zh/usage/kunlunxin_xpu_deployment.md b/docs/zh/usage/kunlunxin_xpu_deployment.md
index b2a2d8feb..901188de7 100644
--- a/docs/zh/usage/kunlunxin_xpu_deployment.md
+++ b/docs/zh/usage/kunlunxin_xpu_deployment.md
@@ -3,25 +3,25 @@
## 支持的模型
|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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.95 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 131072 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9 \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "W4A8" \
--gpu-memory-utilization 0.9 \
--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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-28B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 10 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-424B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 8 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--gpu-memory-utilization 0.7 \
--load-choices "default"|2.3.0|
+|ERNIE-4.5-300B-A47B|32K|WINT8|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-300B-A47B|32K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.95|2.3.0|
+|ERNIE-4.5-300B-A47B|128K|WINT4|8|export XPU_VISIBLE_DEVICES="0,1,2,3,4,5,6,7"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--max-model-len 131072 \
--max-num-seqs 64 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|32K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-21B-A3B|128K|WINT8|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-21B-A3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint4" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-0.3B|32K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 32768 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-0.3B|128K|BF16|1|export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--gpu-memory-utilization 0.9|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
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-0.3B-Paddle \
--port 8188 \
--tensor-parallel-size 1 \
--max-model-len 131072 \
--max-num-seqs 128 \
--quantization "wint8" \
--gpu-memory-utilization 0.9|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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-300B-A47B-W4A8C8-TP4-Paddle \
--port 8188 \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "W4A8" \
--gpu-memory-utilization 0.9|2.3.0|
+|ERNIE-4.5-VL-28B-A3B|32K|WINT8|1|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 \
--tensor-parallel-size 1 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 10 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--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"
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/ERNIE-4.5-VL-424B-A47B-Paddle \
--port 8188 \
--tensor-parallel-size 8 \
--quantization "wint8" \
--max-model-len 32768 \
--max-num-seqs 8 \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
--reasoning-parser ernie-45-vl \
--gpu-memory-utilization 0.7|2.3.0|
|PaddleOCR-VL-0.9B|32K|BF16|1|export FD_ENABLE_MAX_PREFILL=1
export XPU_VISIBLE_DEVICES="0" # 指定任意一张卡
python -m fastdeploy.entrypoints.openai.api_server \
--model PaddlePaddle/PaddleOCR-VL \
--port 8188 \
--metrics-port 8181 \
--engine-worker-queue-port 8182 \
--max-model-len 16384 \
--max-num-batched-tokens 16384 \
--gpu-memory-utilization 0.8 \
--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
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"|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
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 }'|2.3.0|
## 快速开始
@@ -40,8 +40,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--max-model-len 32768 \
--max-num-seqs 64 \
--quantization "wint4" \
- --gpu-memory-utilization 0.9 \
- --load-choices "default"
+ --gpu-memory-utilization 0.9
```
**注意：** 使用 P800 在 4 块 XPU 上进行部署时，由于受到卡间互联拓扑等硬件限制，仅支持以下两种配置方式：
@@ -115,8 +114,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--enable-mm \
--mm-processor-kwargs '{"video_max_frames": 30}' \
--limit-mm-per-prompt '{"image": 10, "video": 3}' \
- --reasoning-parser ernie-45-vl \
- --load-choices "default"
+ --reasoning-parser ernie-45-vl
```
#### 请求服务
@@ -261,8 +259,7 @@ python -m fastdeploy.entrypoints.openai.api_server \
--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"
+ --mm-processor-kwargs '{"image_max_pixels": 12845056 }'
```
### 请求服务