paddleocr-vl 在昆仑p800 推理速度慢，只有25toekn/s。 采用官方的部署，这个正常吗？

[luyike221]

昆仑p800 推理速度慢， 想问是否适配了p800显卡

services:
paddleocr-vl-api:
image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-vl:${API_IMAGE_TAG_SUFFIX}
container_name: paddleocr-vl-api
ports:
- 8080:8080
depends_on:
paddleocr-vlm-server:
condition: service_healthy
user: root
restart: unless-stopped
environment:
- VLM_BACKEND=${VLM_BACKEND:-vllm}
- XPU_VISIBLE_DEVICES=6
command: /bin/bash -c "paddlex --serve --pipeline /home/paddleocr/pipeline_config_${VLM_BACKEND}.yaml --device xpu"
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]
volumes:
- ./pipeline_config_fastdeploy.yaml:/home/paddleocr/pipeline_config.yaml:ro
privileged: true
shm_size: 64G

paddleocr-vlm-server:
image: ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlepaddle/paddleocr-genai-${VLM_BACKEND}-server:${VLM_IMAGE_TAG_SUFFIX}
container_name: paddleocr-vlm-server
user: root
restart: unless-stopped
environment:
- XPU_VISIBLE_DEVICES=6
healthcheck:
test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]
start_period: 300s
privileged: true
shm_size: 64G