Update Dockerfile for vllm wheel version and enhance SHM connector tests

- Updated Dockerfile to use a new vllm wheel version.
- Modified test_put_get_inline to clarify that it always uses SHM and updated metadata assertions.
- Added handling for speculative configuration in GPU model runners to delay clearing connector metadata.
- Refactored payload decoding in OmniGPUModelRunner for better clarity and maintainability.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/worker/test_gpu_generation_model_runner.py

@@ -34,6 +34,7 @@ def _make_runner(multimodal_outputs):
     runner.use_async_scheduling = False
     runner.device = torch.device("cpu")
     runner.supports_mm_inputs = False
+    runner.speculative_config = None
     return runner