[Feature]Support async computation and communication across stages by chunks (#727)

Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: CHEN <116010019@link.cuhk.edu.cn>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/diffusion/worker/gpu_diffusion_model_runner.py

@@ -207,10 +207,11 @@ class GPUDiffusionModelRunner:
                 start_time = time.time()
 
                 while True:
+                    get_key = f"omni_{from_stage}_to_{to_stage}_kv_cache_{req.request_id}"
                     result = self.connector.get(
                         from_stage=from_stage,
                         to_stage=to_stage,
-                        request_id=f"kv_cache_{req.request_id}",
+                        get_key=get_key,
                     )
                     if result:
                         break