Skip to content

Past Status - Tiered Prefix Cache CPU Offloading E2E (GKE GPU LMCache) #3

Past Status - Tiered Prefix Cache CPU Offloading E2E (GKE GPU LMCache)

Past Status - Tiered Prefix Cache CPU Offloading E2E (GKE GPU LMCache) #3

name: Past Status - Tiered Prefix Cache CPU Offloading E2E (GKE GPU LMCache)
on:
workflow_dispatch:
inputs:
workflow_name_query:
description: 'Name of the workflow to be queried'
required: false
type: 'string'
default: 'nightly-e2e-tiered-prefix-cache-gke-cpu-gpu-vllm-lmcache.yaml'
time_window_query:
description: 'How many days in the past to query'
required: true
type: 'string'
default: '5'
branch_query:
description: 'Branch to be queried'
required: false
type: string
default: 'main'
# push:
# branches:
# - main
schedule:
- cron: '0 13 * * *' # 13:00 UTC daily
jobs:
check_for_success:
uses: llm-d/llm-d-infra/.github/workflows/reusable-query-success-past-runs.yaml@main
with:
workflow_name_query: ${{ inputs.workflow_name_query || 'nightly-e2e-tiered-prefix-cache-gke-cpu-gpu-vllm-lmcache.yaml' }}
time_window_query: ${{ inputs.time_window_query || '5' }}
branch_query: ${{ inputs.branch_query || 'main' }}
secrets: inherit