Deprecate --disable-log-requests and replace with --enable-log-requests (#21739)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

tests/config/test_mp_reducer.py

@@ -28,7 +28,6 @@ def test_mp_reducer(monkeypatch):
             max_model_len=32,
             gpu_memory_utilization=0.1,
             disable_log_stats=True,
-            disable_log_requests=True,
         )
 
         async_llm = AsyncLLM.from_engine_args(

tests/mq_llm_engine/test_load.py

@@ -16,7 +16,7 @@ NUM_EXPECTED_TOKENS = 10
 NUM_REQUESTS = 10000
 
 # Scenarios to test for num generated token.
-ENGINE_ARGS = AsyncEngineArgs(model=MODEL, disable_log_requests=True)
+ENGINE_ARGS = AsyncEngineArgs(model=MODEL)
 
 
 @pytest.fixture(scope="function")

tests/v1/engine/test_async_llm.py

@@ -26,12 +26,10 @@ if not current_platform.is_cuda():
 TEXT_ENGINE_ARGS = AsyncEngineArgs(
     model="meta-llama/Llama-3.2-1B-Instruct",
     enforce_eager=True,
-    disable_log_requests=True,
 )
 
 VISION_ENGINE_ARGS = AsyncEngineArgs(model="Qwen/Qwen2-VL-2B-Instruct",
-                                     enforce_eager=True,
-                                     disable_log_requests=True)
+                                     enforce_eager=True)
 
 TEXT_PROMPT = "Hello my name is Robert and"
 

tests/v1/test_async_llm_dp.py

@@ -25,7 +25,6 @@ DP_SIZE = int(os.getenv("DP_SIZE", 2))
 engine_args = AsyncEngineArgs(
     model="ibm-research/PowerMoE-3b",
     enforce_eager=True,
-    disable_log_requests=True,
     tensor_parallel_size=int(os.getenv("TP_SIZE", 1)),
     data_parallel_size=DP_SIZE,
 )