Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
31 lines
929 B
YAML
31 lines
929 B
YAML
{{- if .Values.autoscaling.enabled }}
|
|
apiVersion: autoscaling/v2
|
|
kind: HorizontalPodAutoscaler
|
|
metadata:
|
|
name: "{{ .Release.Name }}-hpa"
|
|
namespace: {{ .Release.Namespace }}
|
|
spec:
|
|
scaleTargetRef:
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
name: vllm
|
|
minReplicas: {{ .Values.autoscaling.minReplicas }}
|
|
maxReplicas: {{ .Values.autoscaling.maxReplicas }}
|
|
metrics:
|
|
{{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
|
|
- type: Resource
|
|
resource:
|
|
name: cpu
|
|
target:
|
|
type: Utilization
|
|
averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
|
|
{{- end }}
|
|
{{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
|
|
- type: Resource
|
|
resource:
|
|
name: memory
|
|
target:
|
|
type: Utilization
|
|
averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
|
|
{{- end }}
|
|
{{- end }} |