mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-19 22:02:06 +00:00
27ed848676
* feat(gaudi): release ready (docs, docker image and vlm ready) * fix(gaudi): add default argument for the dockerfile * fix(gaudi): remove use of latest for gaudi docker image + redid gaudi benchmarking section to include best practices
53 lines
1.2 KiB
YAML
53 lines
1.2 KiB
YAML
name: CI build
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- 'main'
|
|
tags:
|
|
- 'v*'
|
|
pull_request:
|
|
paths:
|
|
- ".github/workflows/build.yaml"
|
|
- "integration-tests/**"
|
|
- "backends/**"
|
|
- "server/**"
|
|
- "proto/**"
|
|
- "router/**"
|
|
- "launcher/**"
|
|
- "Cargo.lock"
|
|
- "rust-toolchain.toml"
|
|
- "Dockerfile"
|
|
- "Dockerfile_amd"
|
|
- "Dockerfile_intel"
|
|
- "Dockerfile.neuron"
|
|
- "Dockerfile_gaudi"
|
|
branches:
|
|
- "main"
|
|
workflow_dispatch:
|
|
inputs:
|
|
release-tests:
|
|
description: "Run release integration tests"
|
|
required: true
|
|
default: false
|
|
type: boolean
|
|
|
|
jobs:
|
|
build:
|
|
strategy:
|
|
# super important if you want to see all results, even if one fails
|
|
# fail-fast is true by default
|
|
fail-fast: false
|
|
matrix:
|
|
hardware: ["cuda", "cuda-trtllm", "rocm", "intel-xpu", "intel-cpu", "neuron", "gaudi"]
|
|
uses: ./.github/workflows/build.yaml # calls the one above ^
|
|
permissions:
|
|
contents: write
|
|
packages: write
|
|
id-token: write
|
|
with:
|
|
hardware: ${{ matrix.hardware }}
|
|
# https://github.com/actions/runner/issues/2206
|
|
release-tests: ${{ inputs.release-tests == true }}
|
|
secrets: inherit
|