From 02134245a9de87131dd764d3cd76f63e5f6f2231 Mon Sep 17 00:00:00 2001
From: Michael Goin <mgoin64@gmail.com>
Date: Tue, 23 Sep 2025 11:01:24 -0400
Subject: [PATCH] [UX] Change kv-cache-memory log level to debug (#25479)

Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
---
 vllm/v1/worker/gpu_worker.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/vllm/v1/worker/gpu_worker.py b/vllm/v1/worker/gpu_worker.py
index ca8734d28b459..ffea9bb35513a 100644
--- a/vllm/v1/worker/gpu_worker.py
+++ b/vllm/v1/worker/gpu_worker.py
@@ -389,7 +389,7 @@ class Worker(WorkerBase):
                 f"utilize gpu memory. Current kv cache memory in use is "
                 f"{int(self.available_kv_cache_memory_bytes)} bytes.")
 
-            logger.info(msg)
+            logger.debug(msg)
 
         # Warm up sampler and preallocate memory buffer for logits and other
         # sampling related tensors of max possible shape to avoid memory