mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-11 12:24:53 +00:00
Create build-trtllm2
This commit is contained in:
parent
994f0ab2ee
commit
5d3d8c0183
51
.github/workflows/build-trtllm2
vendored
Normal file
51
.github/workflows/build-trtllm2
vendored
Normal file
@ -0,0 +1,51 @@
|
||||
name: Build TensorRT-LLM2
|
||||
on:
|
||||
workflow_call:
|
||||
inputs:
|
||||
runs-on:
|
||||
type: string
|
||||
description: "Which instance type to use to run the workflow"
|
||||
required: true
|
||||
|
||||
outputs:
|
||||
docker_image:
|
||||
description: "Reference to the Docker Image build by this workflow"
|
||||
value: ${{ jobs.build-and-push.outputs.docker_image }}
|
||||
label:
|
||||
description: "Label generated for this build"
|
||||
value: ${{ jobs.build-and-push.outputs.label }}
|
||||
|
||||
permissions:
|
||||
contents: read # Required to check out repository.
|
||||
id-token: write # Required to authenticate via OIDC.
|
||||
|
||||
jobs:
|
||||
build-and-push:
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
|
||||
outputs:
|
||||
docker_image: ${{ steps.final.outputs.docker_image }}
|
||||
label: ${ steps.final.outputs.label }}
|
||||
runs-on:
|
||||
group: ${{ inputs.runs-on }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Inject slug/short variables
|
||||
uses: rlespinasse/github-slug-action@v4.4.1
|
||||
|
||||
- name: Extract TensorRT-LLM version
|
||||
run: |
|
||||
echo "TENSORRT_LLM_VERSION=$(grep -oP '([a-z,0-9]{40})' $GITHUB_WORKSPACE/backends/trtllm/cmake/trtllm.cmake)" >> $GITHUB_ENV
|
||||
echo "TensorRT-LLM version: ${{ env.TENSORRT_LLM_VERSION }}"
|
||||
- name: Set LABEL
|
||||
run: |
|
||||
echo "LABEL=trtllm" >> $GITHUB_ENV
|
||||
- name: "Configure AWS Credentials"
|
||||
id: aws-creds
|
||||
uses: aws-actions/configure-aws-credentials@v4
|
||||
with:
|
||||
aws-region: us-east-1
|
||||
role-to-assume: ${{ secrets.AWS_ROLE_GITHUB_TGI_TEST }}
|
||||
role-duration-seconds: 7200
|
||||
output-credentials: true
|
Loading…
Reference in New Issue
Block a user