mmj05

使用vllm-metax0.20.1的也不行，目前问题看是mccl在pod中起不来，这个配置文件需要怎么修改呢

apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
deployment.kubernetes.io/revision: "4"
creationTimestamp: "2026-07-13T08:41:08Z"
generation: 4
managedFields:
- apiVersion: apps/v1
fieldsType: FieldsV1
fieldsV1:
f:spec:
f:progressDeadlineSeconds: {}
f:replicas: {}
f:revisionHistoryLimit: {}
f:selector: {}
f:strategy:
f:type: {}
f:template:
f:metadata:
f:annotations:
.: {}
f:scheduling.k8s.io/group-name: {}
f:labels:
.: {}
f:ai.module: {}
f:gpu: {}
f:log: {}
f:master: {}
f:spec:
f:containers:
k:{"name":"master"}:
.: {}
f:env:
.: {}
k:{"name":"JUPYTER_DIR"}:
.: {}
f:name: {}
f:value: {}
k:{"name":"JUPYTER_PWD"}:
.: {}
f:name: {}
f:value: {}
k:{"name":"LIBCUDA_LOG_LEVEL"}:
.: {}
f:name: {}
f:value: {}
f:imagePullPolicy: {}
f:name: {}
f:ports:
.: {}
k:{"containerPort":22,"protocol":"TCP"}:
.: {}
f:containerPort: {}
f:name: {}
f:protocol: {}
k:{"containerPort":8888,"protocol":"TCP"}:
.: {}
f:containerPort: {}
f:name: {}
f:protocol: {}
f:resources:
.: {}
f:limits:
.: {}
f:cpu: {}
f:memory: {}
f:metax-tech.com/gpu: {}
f:requests:
.: {}
f:cpu: {}
f:memory: {}
f:terminationMessagePath: {}
f:terminationMessagePolicy: {}
f:tty: {}
f:volumeMounts:
.: {}
k:{"mountPath":"/ai/abc"}:
.: {}
f:mountPath: {}
f:name: {}
k:{"mountPath":"/dev/shm"}:
.: {}
f:mountPath: {}
f:name: {}
k:{"mountPath":"/etc/localtime"}:
.: {}
f:mountPath: {}
f:name: {}
k:{"mountPath":"/proc/cpuinfo"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
k:{"mountPath":"/proc/diskstats"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
k:{"mountPath":"/proc/meminfo"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
k:{"mountPath":"/proc/stat"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
k:{"mountPath":"/proc/swaps"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
k:{"mountPath":"/proc/uptime"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
f:workingDir: {}
f:dnsPolicy: {}
f:hostname: {}
f:imagePullSecrets:
.: {}
k:{"name":"harbor"}:
.: {}
f:name: {}
f:nodeSelector:
.: {}
f:gpu: {}
f:gpushare: {}
f:schedulable: {}
f:priorityClassName: {}
f:restartPolicy: {}
f:schedulerName: {}
f:securityContext: {}
f:terminationGracePeriodSeconds: {}
f:volumes:
.: {}
k:{"name":"cpuinfo"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"dbdf9748edfa493cb63bbc7b664d5dcd"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"diskstats"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"meminfo"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"shm"}:
.: {}
f:emptyDir:
.: {}
f:medium: {}
f:name: {}
k:{"name":"stat"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"swaps"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"timezone"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
k:{"name":"uptime"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
manager: Kubernetes Java Client
operation: Update
time: "2026-07-13T08:41:32Z"
- apiVersion: apps/v1
fieldsType: FieldsV1
fieldsV1:
f:spec:
f:template:
f:spec:
f:containers:
k:{"name":"master"}:
f:image: {}
f:volumeMounts:
k:{"mountPath":"/opt/maca"}:
.: {}
f:mountPath: {}
f:name: {}
f:readOnly: {}
f:volumes:
k:{"name":"maca-lib"}:
.: {}
f:hostPath:
.: {}
f:path: {}
f:type: {}
f:name: {}
manager: kubectl-edit
operation: Update
time: "2026-07-13T09:35:16Z"
- apiVersion: apps/v1
fieldsType: FieldsV1
fieldsV1:
f:metadata:
f:annotations:
.: {}
f:deployment.kubernetes.io/revision: {}
f:status:
f:availableReplicas: {}
f:conditions:
.: {}
k:{"type":"Available"}:
.: {}
f:lastTransitionTime: {}
f:lastUpdateTime: {}
f:message: {}
f:reason: {}
f:status: {}
f:type: {}
k:{"type":"Progressing"}:
.: {}
f:lastTransitionTime: {}
f:lastUpdateTime: {}
f:message: {}
f:reason: {}
f:status: {}
f:type: {}
f:observedGeneration: {}
f:readyReplicas: {}
f:replicas: {}
f:updatedReplicas: {}
manager: kube-controller-manager
operation: Update
time: "2026-07-13T09:35:48Z"
name: deploy-resource
namespace: 4b46d3fed77b4b5f99c2c508d4d345ad
resourceVersion: "3404218"
uid: e9ae7300-f384-4519-9d70-fe6e68e11715
spec:
progressDeadlineSeconds: 600
replicas: 1
revisionHistoryLimit: 10
selector:
matchLabels:
ai.module: develop
gpu: MXC550
log: "true"
master: "true"
strategy:
type: Recreate
template:
metadata:
annotations:
scheduling.k8s.io/group-name: pg-resource
creationTimestamp: null
labels:
ai.module: develop
gpu: MXC550
log: "true"
master: "true"
spec:
containers:
- env:
- name: LIBCUDA_LOG_LEVEL
value: "0"
- name: JUPYTER_PWD
value: 33d98b7bacab
- name: JUPYTER_DIR
value: /ai/
image: pub-registry1.metax-tech.com/ai-opentest/master/maca/vllm-metax:0.15.0-maca.ai20260227-177-torch2.8-py312-ubuntu22.04-amd64
imagePullPolicy: IfNotPresent
name: master
ports:
- containerPort: 22
name: ssh
protocol: TCP
- containerPort: 8888
name: jupyter
protocol: TCP
resources:
limits:
cpu: "32"
memory: 256Gi
metax-tech.com/gpu: "8"
requests:
cpu: "32"
memory: 256Gi
terminationMessagePath: /dev/termination-log
terminationMessagePolicy: File
tty: true
volumeMounts:
- mountPath: /dev/shm
name: shm
- mountPath: /etc/localtime
name: timezone
- mountPath: /opt/maca
name: maca-lib
readOnly: true
- mountPath: /proc/cpuinfo
name: cpuinfo
readOnly: true
- mountPath: /proc/diskstats
name: diskstats
readOnly: true
- mountPath: /proc/meminfo
name: meminfo
readOnly: true
- mountPath: /proc/stat
name: stat
readOnly: true
- mountPath: /proc/swaps
name: swaps
readOnly: true
- mountPath: /proc/uptime
name: uptime
readOnly: true
- mountPath: /ai/abc
name: dbdf9748edfa493cb63bbc7b664d5dcd
workingDir: /ai/
dnsPolicy: ClusterFirst
hostname: ai
imagePullSecrets:
- name: harbor
nodeSelector:
gpu: MXC550
gpushare: "false"
schedulable: "true"
priorityClassName: preempt-never
restartPolicy: Always
schedulerName: volcano
securityContext: {}
terminationGracePeriodSeconds: 30
volumes:
- emptyDir:
medium: Memory
name: shm
- hostPath:
path: /usr/share/zoneinfo/Asia/Shanghai
type: ""
name: timezone
- hostPath:
path: /opt/maca
type: Directory
name: maca-lib
- hostPath:
path: /var/lib/lxcfs/proc/cpuinfo
type: File
name: cpuinfo
- hostPath:
path: /var/lib/lxcfs/proc/diskstats
type: File
name: diskstats
- hostPath:
path: /var/lib/lxcfs/proc/meminfo
type: File
name: meminfo
- hostPath:
path: /var/lib/lxcfs/proc/stat
type: File
name: stat
- hostPath:
path: /var/lib/lxcfs/proc/swaps
type: File
name: swaps
- hostPath:
path: /var/lib/lxcfs/proc/uptime
type: File
name: uptime
- hostPath:
path: /zion0/rcmAI/storage/pvc-3c80e2fa-0ae5-4ef0-8a80-40a28e3d50a4_dbdf9748edfa493cb63bbc7b664d5dcd_pvc-dbdf9748edfa493cb63bbc7b664d5dcd
type: ""
name: dbdf9748edfa493cb63bbc7b664d5dcd
status:
availableReplicas: 1
conditions:
- lastTransitionTime: "2026-07-13T09:35:48Z"
lastUpdateTime: "2026-07-13T09:35:48Z"
message: Deployment has minimum availability.
reason: MinimumReplicasAvailable
status: "True"
type: Available
- lastTransitionTime: "2026-07-13T08:41:08Z"
lastUpdateTime: "2026-07-13T09:35:48Z"
message: ReplicaSet "deploy-resource-66bd7659b5" has successfully progressed.
reason: NewReplicaSetAvailable
status: "True"
type: Progressing
observedGeneration: 4
readyReplicas: 1
replicas: 1
updatedReplicas: 1
kind: List
metadata:
resourceVersion: ""
selfLink: ""