CI Cleanup and Parallel Testing #41

	name: Triton Kernel Benchmarking
	on:
	pull_request:
	types: [opened, synchronize]
	workflow_dispatch:
	schedule:
	# Runs at 12:00 PM UTC, which is 5:00 AM PST
	- cron: '0 12 * * *'

	concurrency:
	# A PR number if a pull request and otherwise the commit hash. This cancels
	# queued and in-progress runs for the same PR (presubmit) or commit
	# (postsubmit). The workflow name is prepended to avoid conflicts between
	# different workflows.
	group: ${{ github.workflow }}-${{ github.event.number \|\| github.sha }}
	cancel-in-progress: true

	jobs:
	kernel-bench:
	runs-on: amdgpu-mi250-x86-64
	env:
	KERNEL_VENV_DIR: ${{ github.workspace }}/triton_bench
	steps:
	- name: Checkout Repo
	uses: actions/checkout@v4

	- name: Setup Python
	uses: actions/setup-python@v5
	with:
	python-version: "3.11"

	- name : Set Test File
	run: \|
	python3.11 ci-tools/parse.py --test "${{ github.event.pull_request.body }}"
	echo "TEST_FILE=$TEST_FILE" >> $GITHUB_ENV

	- name: Setup Triton Python Venv
	run: \|
	python3.11 -m venv ${KERNEL_VENV_DIR}
	source ${KERNEL_VENV_DIR}/bin/activate
	pip install --upgrade pip
	pip install --pre pytorch-triton-rocm==3.1.0+cf34004b8a torch==2.6.0.dev20241023+rocm6.2 --index-url https://download.pytorch.org/whl/nightly/rocm6.2
	pip install pytest-xdist
	pip install -r requirements.txt

	- name: Run Kernel Benchmarking
	run: \|
	source ${KERNEL_VENV_DIR}/bin/activate
	pip freeze
	pytest kernels/${TEST_FILE} -s -n 4

	- uses: actions/upload-artifact@master
	with:
	name: perf-artifacts
	path: ./perf-artifacts/*/.csv

Provide feedback