需要支持hps:paddlex3.7-gpu 镜像 和 部署 PP-OCRv6_medium模型加载问题

Search before asking

• I have searched the PaddleOCR Docs and found no similar bug report.
• I have searched the PaddleOCR Issues and found no similar bug report.
• I have searched the PaddleOCR Discussions and found no similar bug report.

Bug (问题描述)

ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.7-gpu 有3.7了，应该支持下3.7镜像

extline_ori' successfully.]: 100%|███████████████████████| 735/735 [00:00<00:00, 2.05kB/s] Creating model: ('PP-OCRv6_server_det', None, None) | 5.00M/6.43M [00:00<00:00, 9.67MB/s] 0624 11:06:04.279053 49 pb_stub.cc:352] Failed to initialize Python stub: ValueError: No engine bindings registered for model 'PP-OCRv6_server_det'.

extline_ori' successfully. Creating model: ('PP-OCRv6_medium_det', None, None) | 5.00M/6.43M [00:00<00:00, 12.1MB/s] 0624 11:16:11.995281 49 pb_stub.cc:352] Failed to initialize Python stub: ValueError: No engine bindings registered for model 'PP-OCRv6_medium_det'.

模型加载报错

‍♂️ Environment (运行环境)

docker

Minimal Reproducible Example (最小可复现问题的Demo)

docker run
-it
--gpus '"device=1"'
--memory 6g --memory-swap 6g
--shm-size 2g
-e PADDLEX_HPS_DEVICE_TYPE=gpu
-e PADDLEX_HPS_USE_HPIP=0
-v paddleocr/3.6/paddlex_hps_OCR_sdk/server:/app
-w /app
--init
--name paddlex-ocrv6-gpu01
--shm-size 12g
ccr-2vdh3abv-pub.cnc.bj.baidubce.com/paddlex/hps:paddlex3.6-gpu
/bin/bash server.sh