Triton Kernel Benchmarking #20

	name: Triton Kernel Benchmarking
	on:
	pull_request:
	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
	steps:
	- name: Checkout Repo
	uses: actions/checkout@v4

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

	- name: Setup Triton Python Venv
	run: \|
	python3.11 -m venv triton_bench
	source triton_bench/bin/activate
	pip install --upgrade pip
	pip install --pre pytorch-triton-rocm torch --index-url https://download.pytorch.org/whl/nightly/rocm6.2
	pip install -r requirements.txt

	- name: Run Kernel Benchmarking
	run: \|
	source triton_bench/bin/activate
	pip freeze
	pytest -s kernels

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

Provide feedback