fix: fix qwen3.5 nightly (#2241)

Signed-off-by: Yuki Huang <yukih@nvidia.com>

Author: yuki-97

examples/configs/recipes/llm/grpo-qwen3.5-35ba3b-2n8g-automodel-ep16.yaml

@@ -28,6 +28,7 @@ policy:
   generation:
     vllm_cfg:
       tensor_parallel_size: 8
+      # set to eager mode to mitigate https://github.com/vllm-project/vllm/issues/36237
       enforce_eager: true
 logger:
   wandb_enabled: true

examples/configs/recipes/llm/grpo-qwen3.5-35ba3b-2n8g-megatron-ep16.yaml

@@ -20,6 +20,8 @@ policy:
   generation:
     vllm_cfg:
       tensor_parallel_size: 8
+      # set to eager mode to mitigate https://github.com/vllm-project/vllm/issues/36237
+      enforce_eager: true
 logger:
   wandb_enabled: true
   tensorboard_enabled: true