fix(infra): update GCP runner to v2.332.0 and resolve rebase import conflicts

Runner 2.317.0 does not support node24 required by actions/checkout@v6,
causing 'Set up job' failures on dynamically provisioned GCP instances.

Key changes:
- Bump RUNNER_VERSION from 2.317.0 to 2.332.0 in test-areal.yml and build-docker-image.yml
- Remove duplicate imports in test_rollout_controller.py from rebase with PR #996

Author: garrett4wade

.github/workflows/build-docker-image.yml

@@ -14,7 +14,7 @@ permissions:
 env:
   GCP_PROJECT_ID: ${{ secrets.GCP_PROJECT_ID }}
   VALIDATOR_LABELS: gcp-docker-validator
-  RUNNER_VERSION: '2.317.0'
+  RUNNER_VERSION: '2.332.0'
   IMAGE_NAME: ghcr.io/inclusionai/areal-runtime
   IMAGE_TAG: test
 

.github/workflows/test-areal.yml

@@ -39,7 +39,7 @@ concurrency:
 
 env:
   GCP_PROJECT_ID: ${{ secrets.GCP_PROJECT_ID }}
-  RUNNER_VERSION: '2.317.0'
+  RUNNER_VERSION: '2.332.0'
   GCP_OS_IMAGE: areal-cicd-test-202602030
 
 jobs:

tests/grpo/config_archon.yaml

@@ -1,5 +1,7 @@
 experiment_name: tests-grpo
 trial_name: trial
+scheduler:
+  type: local
 cluster:
   n_nodes: 1
   n_gpus_per_node: 2

tests/grpo/config_archon_vllm.yaml

@@ -1,5 +1,7 @@
 experiment_name: tests-grpo
 trial_name: trial
+scheduler:
+  type: local
 cluster:
   n_nodes: 1
   n_gpus_per_node: 2
@@ -34,8 +36,6 @@ vllm:
   model: ${actor.path}
   seed: ${seed}
   skip_tokenizer_init: false
-  max_model_len: 128
-  gpu_memory_utilization: 0.2
 gconfig:
   n_samples: 4
   max_new_tokens: 1024

tests/grpo/config_fsdp.yaml

@@ -1,5 +1,7 @@
 experiment_name: tests-grpo
 trial_name: trial
+scheduler:
+  type: local
 cluster:
   n_nodes: 1
   n_gpus_per_node: 2

tests/grpo/config_fsdp_vllm.yaml

@@ -1,5 +1,7 @@
 experiment_name: tests-grpo
 trial_name: trial
+scheduler:
+  type: local
 cluster:
   n_nodes: 1
   n_gpus_per_node: 2
@@ -34,8 +36,6 @@ vllm:
   model: ${actor.path}
   seed: ${seed}
   skip_tokenizer_init: false
-  max_model_len: 128
-  gpu_memory_utilization: 0.2
 gconfig:
   n_samples: 4
   max_new_tokens: 1024

tests/grpo/config_megatron.yaml

@@ -1,5 +1,7 @@
 experiment_name: tests-grpo
 trial_name: trial
+scheduler:
+  type: local
 cluster:
   n_nodes: 1
   n_gpus_per_node: 2

tests/grpo/config_megatron_vllm.yaml

@@ -1,5 +1,7 @@
 experiment_name: tests-grpo
 trial_name: trial
+scheduler:
+  type: local
 cluster:
   n_nodes: 1
   n_gpus_per_node: 2
@@ -34,8 +36,6 @@ vllm:
   model: ${actor.path}
   seed: ${seed}
   skip_tokenizer_init: false
-  max_model_len: 128
-  gpu_memory_utilization: 0.2
 gconfig:
   n_samples: 4
   max_new_tokens: 1024

tests/grpo/test_grpo.py

@@ -72,11 +72,7 @@ def test_grpo(tmp_path: Path, backend: str, inference: str) -> None:
             sort_keys=False,
         )
 
-    cmd = (
-        Command("python")
-        .bake(m="areal.infra.launcher.local")
-        .bake(os.path.join(base_dir, "entrypoint.py"))
-    )
+    cmd = Command("python").bake(os.path.join(base_dir, "entrypoint.py"))
 
     cmd(
         f"cluster.fileroot={tmp_path}",

tests/test_rollout_controller.py

@@ -20,8 +20,6 @@
     SchedulingSpec,
     SGLangConfig,
 )
-from areal.api.io_struct import ModelRequest, ParamSpec, WeightUpdateMeta
-from areal.api.scheduler_api import Worker
 from areal.infra import RolloutController
 from areal.infra.scheduler.local import LocalScheduler
 from areal.utils.hf_utils import load_hf_tokenizer