unable to request 2 vgpu

[bx0216]

I have a 4090 GPU, and configure the time slicing(nvidia.com/gpu 4) shared this GPU,
and configure volcano vgpu device plugin with:
args:
- --mig-strategy=none
- --device-split-count=4
when I use the flowing to create a pod (try to request 2 vgpu)
apiVersion: v1
kind: Pod
metadata:
name: pod2
spec:
restartPolicy: OnFailure
schedulerName: volcano
containers:

• image: ubuntu:20.04
  name: pod1-ctr
  command: ["sleep"]
  args: ["100000"]
  resources:
  limits:
  volcano.sh/vgpu-memory: 2048
  volcano.sh/vgpu-number: 2

the pod always is "pending" state.
use the "kubectl describe" to get the info of this pod, report the flowing:

---

Warning FailedScheduling 36m volcano 0/3 nodes are unavailable: 1 no enough gpu cards on node bjsw-devsrv01, 2 Insufficient volcano.sh/vgpu-number.