Skip to content

Add basic correctness 2 GPU tests to 4 GPU pipeline #5518

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

Merged
merged 1 commit into from
Jun 16, 2024
Merged

Add basic correctness 2 GPU tests to 4 GPU pipeline #5518

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
8 changes: 6 additions & 2 deletions .buildkite/test-pipeline.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ steps:
working_dir: "/vllm-workspace/tests"
num_gpus: 2

- label: Distributed Tests
- label: Distributed Tests (2 GPUs)
mirror_hardwares: [amd]
working_dir: "/vllm-workspace/tests"
num_gpus: 2
Expand All @@ -50,12 +50,16 @@ steps:
- CUDA_VISIBLE_DEVICES=0,1 pytest -v -s test_sharded_state_loader.py
- CUDA_VISIBLE_DEVICES=0,1 pytest -v -s distributed/test_utils.py

- label: Distributed Tests (Multiple Groups)
- label: Distributed Tests (4 GPUs)
#mirror_hardwares: [amd]
working_dir: "/vllm-workspace/tests"
num_gpus: 4
commands:
- pytest -v -s distributed/test_pynccl.py
# We want to test that models which use 2 GPUs work with 4 GPUs, which is why we duplicate them here.
# See https://github.com/vllm-project/vllm/pull/5473#issuecomment-2166601837 for context.
- TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=ray pytest -v -s distributed/test_basic_distributed_correctness.py
- TEST_DIST_MODEL=facebook/opt-125m DISTRIBUTED_EXECUTOR_BACKEND=mp pytest -v -s distributed/test_basic_distributed_correctness.py

- label: Engine Test
mirror_hardwares: [amd]
Expand Down