Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add attention backend tests to more-tests.yml #1480

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add attention backend tests to more-tests.yml #1480

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 62 additions & 0 deletions .github/workflows/more-tests.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ jobs:
gpu-arch-version: "12.4"
timeout: 60
script: |
set -xeou pipefail
echo "::group::Print machine info"
uname -a
echo "::endgroup::"
Expand Down Expand Up @@ -83,3 +84,64 @@ jobs:
echo "tests complete"
echo "******************************************"
echo "::endgroup::"

test-sdpa-backends:
permissions:
id-token: write
contents: read
uses: pytorch/test-infra/.github/workflows/linux_job_v2.yml@main
with:
runner: linux.g5.4xlarge.nvidia.gpu
gpu-arch-type: cuda
gpu-arch-version: "12.4"
timeout: 60
script: |
set -xeou pipefail
echo "::group::Print machine info"
uname -a
echo "::endgroup::"

echo "::group::Download checkpoints"
# Install requirements
./install/install_requirements.sh cuda
pip3 list
python3 -c 'import torch;print(f"torch: {torch.__version__, torch.version.git_version}")'
echo "::endgroup::"

echo "::group::Download checkpoints"
mkdir -p checkpoints/stories15M
pushd checkpoints/stories15M
wget https://huggingface.co/karpathy/tinyllamas/resolve/main/stories15M.pt
wget https://github.com/karpathy/llama2.c/raw/master/tokenizer.model
popd
echo "::endgroup::"

echo "::group::Run inference"
export MODEL_PATH=checkpoints/stories15M/stories15M.pt
export MODEL_NAME=stories15M
export MODEL_DIR=/tmp

for DEVICE in cpu cuda; do
for DTYPE in bfloat16 float16 float32; do
for SDPA in 'math' 'flash_attention' 'efficient_attention' 'cudnn_attention'; do
echo "******************************************************************"
echo "******* $DEVICE $DTYPE $SDPA "
###################################################################
# Python execution interpreted vanilla
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --attention-backend ${SDPA} --device ${DEVICE} --dtype ${DTYPE} --temperature 0
###################################################################
# prefill, and compile and prefill compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --attention-backend ${SDPA} --device ${DEVICE} --dtype ${DTYPE} --temperature 0 --compile --compile-prefill
###################################################################
# sequential prefill
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --attention-backend ${SDPA} --device ${DEVICE} --dtype ${DTYPE} --temperature 0 --sequential-prefill
###################################################################
# prefill, and compile
python torchchat.py generate --checkpoint-path ${MODEL_PATH} --attention-backend ${SDPA} --device ${DEVICE} --dtype ${DTYPE} --temperature 0 --sequential-prefill --compile
done
done
done

echo "tests complete"
echo "******************************************"
echo "::endgroup::"
Loading