Lower memory usage during AttnFuncWithCP.forward #4370

	# Copyright (c) 2022-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
	#
	# See LICENSE for license information.

	# A workflow to trigger TE build on GitHub
	name: 'Build'
	on:
	pull_request:
	workflow_dispatch:
	jobs:
	pytorch:
	name: 'PyTorch'
	runs-on: ubuntu-latest
	container:
	image: nvcr.io/nvidia/pytorch:24.05-py3
	options: --user root
	steps:
	- name: 'Checkout'
	uses: actions/checkout@v3
	with:
	submodules: recursive
	- name: 'Build'
	run: pip install . -v --no-deps
	env:
	NVTE_FRAMEWORK: pytorch
	MAX_JOBS: 1
	- name: 'Sanity check'
	run: python tests/pytorch/test_sanity_import.py
	jax:
	name: 'JAX'
	runs-on: ubuntu-latest
	container:
	image: ghcr.io/nvidia/jax:jax
	options: --user root
	steps:
	- name: 'Checkout'
	uses: actions/checkout@v3
	with:
	submodules: recursive
	- name: 'Build'
	run: pip install . -v
	env:
	NVTE_FRAMEWORK: jax
	- name: 'Sanity check'
	run: python tests/jax/test_sanity_import.py
	paddle:
	name: 'PaddlePaddle'
	runs-on: ubuntu-latest
	container:
	image: nvcr.io/nvidia/paddlepaddle:24.05-py3
	options: --user root
	steps:
	- name: 'Checkout'
	uses: actions/checkout@v3
	with:
	submodules: recursive
	- name: 'Build'
	run: pip install . -v
	env:
	NVTE_FRAMEWORK: paddle
	- name: 'Sanity check'
	run: python tests/paddle/test_sanity_import.py

Provide feedback