[Rebase] Rebase to vllm releases/v0.22.0 (#3891)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: ZhengWG <zwg0606@gmail.com>
Signed-off-by: david6666666 <530634352@qq.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: nainiu258 <cperfect02@163.com>
Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com>
Co-authored-by: Zheng Wengang <zwg0606@gmail.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com>
Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

tests/dfx/perf/scripts/run_diffusion_benchmark.py

@@ -223,8 +223,12 @@ def _get_open_port() -> int:
         return s.getsockname()[1]
 
 
-def _wait_for_port(host: str, port: int, timeout: int = 1200) -> None:
-    """Block until the given host:port accepts connections or timeout expires."""
+def _wait_for_port(host: str, port: int, timeout: int = 1200, proc: subprocess.Popen | None = None) -> None:
+    """Block until the given host:port accepts connections or timeout expires.
+
+    If *proc* is provided, also monitors the process; raises RuntimeError
+    immediately if the server process exits before the port becomes available.
+    """
     start = time.time()
     while time.time() - start < timeout:
         try:
@@ -234,6 +238,10 @@ def _wait_for_port(host: str, port: int, timeout: int = 1200) -> None:
                     return
         except Exception:
             pass
+        if proc is not None:
+            ret = proc.poll()
+            if ret is not None:
+                raise RuntimeError(f"Server process exited with code {ret} before port {host}:{port} became ready")
         time.sleep(2)
     raise RuntimeError(f"Server did not start on {host}:{port} within {timeout}s")
 
@@ -331,7 +339,7 @@ class DiffusionServer:
             env=env,
             cwd=str(Path(__file__).parent.parent.parent.parent),
         )
-        _wait_for_port(self.host, self.port)
+        _wait_for_port(self.host, self.port, proc=self.proc)
         print(f"DiffusionServer ready on {self.host}:{self.port}")
 
     def __enter__(self):