Docs

Fixed FP8 fake quantization to use fp32 amax scaling; Added support for FP8 per-channel quantization #821

	name: Docs

	on:
	pull_request:
	branches: [main, release/*]
	push:
	branches: [main]
	schedule:
	- cron: "0 0 * * *" # Nightly
	workflow_dispatch: # On-demand

	# Cancel previous runs if new commit is pushed
	concurrency:
	group: ${{ github.workflow }}-${{ github.event.pull_request.number \|\| github.sha }}
	cancel-in-progress: true

	# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
	permissions:
	contents: read
	pages: write
	id-token: write

	jobs:
	build-docs:
	runs-on: ubuntu-latest
	timeout-minutes: 30
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: "3.12"
	- name: Build docs
	run: pip install tox && tox -e build-docs
	- name: Upload docs artifact
	if: github.event_name == 'push'
	uses: actions/upload-pages-artifact@v3
	with:
	path: docs/build/html

	deploy-gh-pages:
	if: github.event_name == 'push'
	needs: build-docs
	runs-on: ubuntu-latest
	environment:
	name: github-pages
	url: ${{ steps.deployment.outputs.page_url }}
	steps:
	- id: deployment
	uses: actions/deploy-pages@v4

Provide feedback