fix: log warning when disable cuda graph (#5209)

Author: zhyncs

python/sglang/srt/model_executor/cuda_graph_runner.py

@@ -269,10 +269,10 @@ def __init__(self, model_runner: ModelRunner):
             raise Exception(
                 f"Capture cuda graph failed: {e}\n"
                 "Possible solutions:\n"
-                "1. disable cuda graph by --disable-cuda-graph\n"
-                "2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)\n"
+                "1. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)\n"
+                "2. set --cuda-graph-max-bs to a smaller value (e.g., 32)\n"
                 "3. disable torch compile by not using --enable-torch-compile\n"
-                "4. set --cuda-graph-max-bs to a smaller value (e.g., 32)\n"
+                "4. disable cuda graph by --disable-cuda-graph\n"
                 "Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose \n"
             )
 

python/sglang/srt/model_executor/model_runner.py

@@ -924,6 +924,12 @@ def init_cuda_graphs(self):
             return
 
         if self.server_args.disable_cuda_graph:
+            logger.warning(
+                "\n\nCUDA Graph is DISABLED.\n"
+                "This will cause significant performance degradation.\n"
+                "CUDA Graph should almost never be disabled in most usage scenarios.\n"
+                "If you encounter OOM issues, please try setting --mem-fraction-static to a lower value (such as 0.8 or 0.7) instead of disabling CUDA Graph.\n"
+            )
             return
 
         tic = time.time()

python/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py

@@ -84,10 +84,10 @@ def __init__(self, eagle_worker: EAGLEWorker):
             raise Exception(
                 f"Capture cuda graph failed: {e}\n"
                 "Possible solutions:\n"
-                "1. disable cuda graph by --disable-cuda-graph\n"
-                "2. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)\n"
-                "3. disable torch compile by not using --enable-torch-compile\n"
-                "4. specify --dtype to the same dtype (e.g. bfloat16)\n"
+                "1. set --mem-fraction-static to a smaller value (e.g., 0.8 or 0.7)\n"
+                "2. disable torch compile by not using --enable-torch-compile\n"
+                "3. specify --dtype to the same dtype (e.g. bfloat16)\n"
+                "4. disable cuda graph by --disable-cuda-graph\n"
                 "Open an issue on GitHub https://github.com/sgl-project/sglang/issues/new/choose \n"
             )