DeepSeek-R1 昇腾910B2 拉不起来推理服务
收藏回复举报
DeepSeek-R1 昇腾910B2 拉不起来推理服务
t('forum.solved') 已解决
发表于2025-08-22 10:37:49
0 查看

容器启动命令

docker run -itd --privileged --name=deepseek-r1 --net=host
--shm-size 500g
--device=/dev/davinci0
--device=/dev/davinci1
--device=/dev/davinci2
--device=/dev/davinci3
--device=/dev/davinci4
--device=/dev/davinci5
--device=/dev/davinci6
--device=/dev/davinci7
--device=/dev/davinci_manager
--device=/dev/hisi_hdc
--device /dev/devmm_svm
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver
-v /usr/local/sbin:/usr/local/sbin
-v /usr/local/dcmi:/usr/local/dcmi
-v /usr/bin/hccn_tool:/usr/bin/hccn_tool
-v /usr/local/sbin/npu-smi:/usr/local/sbin/npu-smi
-v /usr/local/Ascend/firmware:/usr/local/Ascend/firmware
-v /etc/hccn.conf:/etc/hccn.conf
-v /usr/local/Ascend/add-ons/:/usr/local/Ascend/add-ons/
-v /var/log/npu/slog/:/var/log/npu/slog
-v /var/log/npu/profiling/:/var/log/npu/profiling
-v /var/log/npu/dump/:/var/log/npu/dump
-v /var/log/npu/:/usr/slog
-v /data:/data
registry.modelers.cn/base_image/mindie:2.0.T3-800I-A2-py311-openeuler24.03-lts-aarch64
/bin/bash

环境变量

export WORLD_SIZE=8 export NPU_MEMORY_FRACTION=0.95 export ASCEND_RT_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 export ATB_LLM_BENCHMARK_ENABLE=1 export ATB_LLM_ENABLE_AUTO_TRANSPOSE=0 export OMP_NUM_THREADS=1

配置修改

vim /usr/local/Ascend/mindie/latest/mindie-service/conf/config.json "httpsEnabled" : false, "npuDeviceIds" : [[0,1,2,3,4,5,6,7]], "modelName" : "DeepSeek-R1-0528-w4a8", "modelWeightPath" : "/data/DeepSeek-R1-0528-w4a8", "worldSize" : 8,

启动

cd /usr/local/Ascend/mindie/latest/mindie-service/bin ./mindieservice_daemon

报错日志

initialize_distributed has been Set [ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared! [ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared! [ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared! [ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared! [ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared! [ERROR] TBE Subprocess[task_distribute] raise error[], main process disappeared! ConnectionRefusedError: [Errno 111] Connection refused

我要发帖子