From da55494a125979ffc9d4c1f17d593175cb076bf4 Mon Sep 17 00:00:00 2001
From: Anshul Desai <36732940+AnshulDesai@users.noreply.github.com>
Date: Thu, 3 Sep 2026 21:25:30 -0700
Subject: [PATCH] docs: note that enforce_eager also disables torch.compile
 (#55271)

Signed-off-by: Anshul Desai <36732940+AnshulDesai@users.noreply.github.com>
---
 vllm/config/model.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/vllm/config/model.py b/vllm/config/model.py
index 1598087028..d2bb65ea42 100644
--- a/vllm/config/model.py
+++ b/vllm/config/model.py
@@ -242,7 +242,10 @@ class ModelConfig:
     """Whether to always use eager-mode PyTorch. If True, we will disable CUDA
     graph and always execute the model in eager mode. If False, we will use
     CUDA graph and eager execution in hybrid for maximal performance and
-    flexibility."""
+    flexibility.
+
+    NOTE: This disables both `torch.compile` and CUDA graphs, and is
+    equivalent to setting `-cc.mode=none -cc.cudagraph_mode=none`."""
     enable_return_routed_experts: bool = False
     """Whether to return routed experts."""
     return_sampling_mask: bool = False