[Core] Performance fix for orchestrator bottleneck: separates inter-stage from client outputs (#4527)

Signed-off-by: yinpeiqi <yinpeiqi809@gmail.com>
Co-authored-by: Chenguang ZHENG <645327136@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>

tests/worker/test_gpu_generation_model_runner.py

@@ -40,6 +40,7 @@ def _make_runner(multimodal_outputs):
     runner.supports_mm_inputs = False
     runner.speculative_config = None
     runner.routed_experts_initialized = False
+    runner._async_chunk = False
     return runner