diff --git a/.github/workflows/sandbox.yml b/.github/workflows/sandbox.yml index cd1f497e0db..bffdd2d5886 100644 --- a/.github/workflows/sandbox.yml +++ b/.github/workflows/sandbox.yml @@ -47,5 +47,5 @@ jobs: pip3 install vllm==0.5.4 - name: Running sandbox tests on 8 L20 GPUs run: | - cd tests/sandbox + cd tests/utils/reward_score pytest -s -x . diff --git a/.github/workflows/ray_gpu_test.yml b/.github/workflows/single_controller_unit_tests.yml similarity index 95% rename from .github/workflows/ray_gpu_test.yml rename to .github/workflows/single_controller_unit_tests.yml index 8d8337fdd71..650c80a07a2 100644 --- a/.github/workflows/ray_gpu_test.yml +++ b/.github/workflows/single_controller_unit_tests.yml @@ -1,4 +1,4 @@ -name: ray_gpu +name: single_controller_unit_tests on: # Trigger the workflow on push or pull request, @@ -26,7 +26,7 @@ permissions: contents: read jobs: - ray_gpu: + single_controller_unit_tests: runs-on: [L20x8] timeout-minutes: 10 # Increase this timeout value as needed env: diff --git a/tests/sandbox/test_sandbox.py b/tests/utils/reward_score/test_sandbox.py similarity index 100% rename from tests/sandbox/test_sandbox.py rename to tests/utils/reward_score/test_sandbox.py diff --git a/verl/trainer/ppo/ray_trainer.py b/verl/trainer/ppo/ray_trainer.py index e1fcbf11342..f805798b806 100644 --- a/verl/trainer/ppo/ray_trainer.py +++ b/verl/trainer/ppo/ray_trainer.py @@ -772,7 +772,7 @@ def init_workers(self): self.async_rollout_mode = True self.async_rollout_manager = AsyncLLMServerManager( - config=self.config.actor_rollout_ref, + config=self.config, worker_group=self.actor_rollout_wg, ) diff --git a/verl/utils/checkpoint/checkpoint_manager.py b/verl/utils/checkpoint/checkpoint_manager.py index 076a319bbca..31a2bacf924 100644 --- a/verl/utils/checkpoint/checkpoint_manager.py +++ b/verl/utils/checkpoint/checkpoint_manager.py @@ -150,7 +150,7 @@ def find_latest_ckpt_path(path, directory_format="global_step_{}"): tracker_file = get_checkpoint_tracker_filename(path) if not os.path.exists(tracker_file): - print("Checkpoint tracker file does not exist: %s", tracker_file) + print(f"Checkpoint tracker file does not exist: {tracker_file}") return None with open(tracker_file, "rb") as f: