Fix install instructions and pyproject.tomls (#11781)

python/sglang/srt/model_executor/model_runner.py

@@ -623,7 +623,7 @@ class ModelRunner:
             server_args.disable_chunked_prefix_cache = True
 
         if not server_args.disable_chunked_prefix_cache:
-            logger.info("Chunked prefix cache is turned on.")
+            log_info_on_rank0(logger, "Chunked prefix cache is turned on.")
 
         if server_args.attention_backend == "aiter":
             if self.model_config.context_len > 8192:

python/sglang/srt/server_args.py

@@ -253,7 +253,6 @@ class ServerArgs:
     log_requests: bool = False
     log_requests_level: int = 2
     crash_dump_folder: Optional[str] = None
-    crash_on_nan: bool = False
     show_time_cost: bool = False
     enable_metrics: bool = False
     enable_metrics_for_all_schedulers: bool = False
@@ -1899,12 +1898,6 @@ class ServerArgs:
             default=ServerArgs.crash_dump_folder,
             help="Folder path to dump requests from the last 5 min before a crash (if any). If not specified, crash dumping is disabled.",
         )
-        parser.add_argument(
-            "--crash-on-nan",
-            type=str,
-            default=ServerArgs.crash_on_nan,
-            help="Crash the server on nan logprobs.",
-        )
         parser.add_argument(
             "--show-time-cost",
             action="store_true",