Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

misc(backend): attempt to run the tests?

This commit is contained in:
Morgan Funtowicz 2024-12-21 12:17:32 +01:00
parent 11f348119f
commit 462dcfea85
1 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
.github/workflows/build_trtllm.yaml vendored
View File

@ -119,15 +119,16 @@ jobs:
cache-to: type=s3,region=us-east-1,bucket=ci-docker-buildx-cache,name=text-generation-inference-cache-${{ env.LABEL }},mode=min,access_key_id=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_ACCESS_KEY_ID }},secret_access_key=${{ secrets.S3_CI_DOCKER_BUILDX_CACHE_SECRET_ACCESS_KEY }},mode=min
tests:
needs: build
runs-on:
group: aws-g6-12xl-plus-priv-cache
container:
image:
registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm:${{ env.LABEL }}
credentials:
username: ${{ secrets.REGISTRY_USERNAME }}
password: ${{ secrets.REGISTRY_PASSWORD }}
options: --gpus all --net=host
container:
image:
registry.internal.huggingface.tech/api-inference/community/text-generation-inference/tensorrt-llm:${{ env.LABEL }}
credentials:
username: ${{ secrets.REGISTRY_USERNAME }}
password: ${{ secrets.REGISTRY_PASSWORD }}
options: --gpus all --net=host
steps:
- name: Run C++/CUDA tests