一、软硬件信息
1. 服务器厂家:浪潮
2. 沐曦GPU型号:沐曦C500
3. 操作系统内核版本:Linux node1 6.8.0-53-generic #55-Ubuntu SMP PREEMPT_DYNAMIC Fri Jan 17 15:37:52 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux
4. 是否开启CPU虚拟化:否
5. mx-smi回显:
mx-smi version: 2.2.9
=================== MetaX System Management Interface Log ===================
Timestamp : Thu Oct 29 21:46:29 2026
Attached GPUs : 4
+---------------------------------------------------------------------------------+
| MX-SMI 2.2.9 Kernel Mode Driver Version: 3.4.4 |
| MACA Version: 3.3.0.15 BIOS Version: 1.30.0.0 |
|------------------+-----------------+---------------------+----------------------|
| Board Name | GPU Persist-M | Bus-id | GPU-Util sGPU-M |
| Pwr:Usage/Cap | Temp Perf | Memory-Usage | GPU-State |
|==================+=================+=====================+======================|
| 0 MetaX C500 | 0 Off | 0000:04:00.0 | 0% Disabled |
| 57W / 350W | 36C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 1 MetaX C500 | 1 Off | 0000:05:00.0 | 0% Disabled |
| 57W / 350W | 37C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 2 MetaX C500 | 2 Off | 0000:63:00.0 | 0% Disabled |
| 59W / 350W | 35C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 3 MetaX C500 | 3 Off | 0000:64:00.0 | 0% Disabled |
| 58W / 350W | 36C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
+---------------------------------------------------------------------------------+
| Process: |
| GPU PID Process Name GPU Memory |
| Usage(MiB) |
|=================================================================================|
| no process found |
+---------------------------------------------------------------------------------+
6. docker info回显:
root@node1:~# docker info
Client: Docker Engine - Community
Version: 28.3.3
Context: default
Debug Mode: false
Plugins:
buildx: Docker Buildx (Docker Inc.)
Version: v0.30.1
Path: /usr/libexec/docker/cli-plugins/docker-buildx
compose: Docker Compose (Docker Inc.)
Version: v5.0.0
Path: /usr/libexec/docker/cli-plugins/docker-compose
Server:
Containers: 17
Running: 17
Paused: 0
Stopped: 0
Images: 18
Server Version: 28.3.3
Storage Driver: overlay2
Backing Filesystem: xfs
Supports d_type: true
Using metacopy: false
Native Overlay Diff: true
userxattr: false
Logging Driver: json-file
Cgroup Driver: systemd
Cgroup Version: 2
Plugins:
Volume: local
Network: bridge host ipvlan macvlan null overlay
Log: awslogs fluentd gcplogs gelf journald json-file local splunk syslog
CDI spec directories:
/etc/cdi
/var/run/cdi
Swarm: inactive
Runtimes: io.containerd.runc.v2 runc
Default Runtime: runc
Init Binary: docker-init
containerd version: dea7da592f5d1d2b7755e3a161be07f43fad8f75
runc version: v1.3.4-0-gd6d73eb8
init version: de40ad0
Security Options:
apparmor
seccomp
Profile: builtin
cgroupns
Kernel Version: 6.8.0-53-generic
Operating System: Ubuntu 24.04.3 LTS
OSType: linux
Architecture: x86_64
CPUs: 192
Total Memory: 377.5GiB
Name: node1
ID: 5a09d43b-16cc-4d6e-9553-d02860e1ca23
Docker Root Dir: /var/lib/data/docker
Debug Mode: false
Experimental: false
Insecure Registries:
0.0.0.0/0
::1/128
127.0.0.0/8
Live Restore Enabled: false
[DEPRECATION NOTICE]: API is accessible on http://0.0.0.0:2375 without encryption.
Access to the remote API is equivalent to root access on the host. Refer
to the 'Docker daemon attack surface' section in the documentation for
more information: docs.docker.com/go/attack-surface/
In future versions this will be a hard failure preventing the daemon from starting! Learn more at: docs.docker.com/go/api-security/
-
镜像版本:vllm-metax-0.28.0-maca.ai3.8.2.401-torch2.10-py310-ubuntu22.04-amd64
-
启动容器命令:
export CUDA_VISIBLE_DEVICES=0,1,2,3
/opt/conda/bin/vllm serve /mnt/models \
--host 0.0.0.0 \
--port 8080 \
--trust_remote_code \
--served-model-name qwen3827b \
--tensor-parallel-size 4 \
--max-model-len 32768 \
--gpu-memory-utilization 0.90 \
--enable-auto-tool-choice \
--tool-call-parser qwen3_coder \
--reasoning-parser qwen3 -
容器内执行命令:
二、问题现象
请描述详细的问题现象日志。若日志过长,请上传附件(txt格式)。
部署Qwen3.8-27B-W8A8模型,一对话服务就崩了