Skip to content
bench_test

[Core] Use ray queue to put request output tokens back to the api server #16

Sign in to view logs

[Core] Use ray queue to put request output tokens back to the api server

[Core] Use ray queue to put request output tokens back to the api server #16

Workflow file for this run

.github/workflows/bench_test.yml at 565f621
name: bench_test
on:
pull_request:
branches:
- main
jobs:
cancel_previous_workflows:
runs-on: [self-hosted]
timeout-minutes: 3
steps:
- uses: styfle/cancel-workflow-action@0.12.1
with:
all_but_latest: true
bench_tests:
needs: cancel_previous_workflows
runs-on: [self-hosted]
timeout-minutes: 60
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Kill Running Containers
run: |
[[ -n $(docker ps -q) ]] && docker kill $(docker ps -q) || echo "No running containers to kill."
- name: Build And Test
run: ./tools/bench_test.sh
- name: Create comment from file
uses: actions/github-script@v7
with:
script: |
const fs = require('fs');
const filePath = 'performance.txt';
const commentBody = fs.readFileSync(filePath, 'utf8');
await github.rest.issues.createComment({
issue_number: context.issue.number,
owner: context.repo.owner,
repo: context.repo.repo,
body: commentBody
});