Add AMD GPU node for integration test #42

	name: 8 AMD GPU Integration Test

	on:
	push:
	branches: [ main ]
	pull_request:
	schedule:
	# Runs every 6 hours
	- cron: '0 /6 * *'
	concurrency:
	group: unit-test${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_number \|\| github.ref }}
	cancel-in-progress: true

	defaults:
	run:
	shell: bash -l -eo pipefail {0}

	jobs:
	build-test:
	uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
	with:
	runner: linux.rocm.gpu.mi300.8
	gpu-arch-type: rocm
	gpu-arch-version: "6.3"
	upload-artifact: outputs
	use-custom-docker-registry: false
	script: \|
	set -eux
	# The generic Linux job chooses to use base env, not the one setup by the image
	conda install -c conda-forge jq -y
	CONDA_ENV=$(conda env list --json \| jq -r ".envs \| .[-1]")
	conda activate "${CONDA_ENV}"
	pip config --user set global.progress_bar off
	pip install -r requirements.txt
	python -m pip install --force-reinstall --pre torch --index-url https://download.pytorch.org/whl/nightly/rocm6.3
	USE_CPP=0 python -m pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
	# There's perrmission issue in uploading files in artifacts-to-be-uploaded on AMD nodes, thus skip it by creating and storing
	# results in generated-artifacts.
	mkdir generated-artifacts
	python ./tests/integration_tests_amd.py generated-artifacts --ngpu 8

Provide feedback