mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-26 20:42:06 +00:00
9e2fdf57c0
* Removing IPEX_AVAIL. Chose to unify CPU and XPU under `ipex`. Most code is exactly similar except for a very few spots. The biggest number of spots is the kv-cache layout and the flash_xxx.py files. Since those files should be removed soon and factored away, we should not need them. * Forgot a few places. * Unrelated change. * Fixing HF_TOKEN. * HF_TOKEN
43 lines
1.3 KiB
YAML
43 lines
1.3 KiB
YAML
name: Nightly load test
|
|
|
|
on:
|
|
schedule:
|
|
- cron: '0 0 * * 1-5'
|
|
|
|
pull_request:
|
|
paths:
|
|
- ".github/workflows/load_test.yaml"
|
|
branches:
|
|
- 'main'
|
|
|
|
jobs:
|
|
load-tests:
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
|
|
env:
|
|
DOCKER_VOLUME: /cache
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@v3
|
|
|
|
- name: Install k6
|
|
run: |
|
|
curl https://github.com/grafana/k6/releases/download/v0.44.0/k6-v0.44.0-linux-amd64.tar.gz -L | tar xvz --strip-components 1
|
|
|
|
- name: Start starcoder
|
|
run: |
|
|
docker run --name tgi-starcoder --rm --gpus all -p 3000:80 -v /mnt/cache:/data -e HF_TOKEN=${{ secrets.HF_TOKEN }} --pull always -d ghcr.io/huggingface/text-generation-inference:latest --model-id bigcode/starcoder --num-shard 2 --max-batch-total-tokens 32768
|
|
sleep 10
|
|
wget --timeout 10 --retry-on-http-error --waitretry=1 --tries=240 http://localhost:3000/health
|
|
|
|
- name: Run k6
|
|
run: |
|
|
./k6 run load_tests/starcoder_load.js
|
|
|
|
- name: Stop starcoder
|
|
if: ${{ always() }}
|
|
run: |
|
|
docker stop tgi-starcoder || true
|