diff --git a/README.md b/README.md
index 17411735..600840a6 100644
--- a/README.md
+++ b/README.md
@@ -254,7 +254,7 @@ This points to your localhost server. Alternatively, for OpenAI, you can use
 The section for vllm can then be removed, as it is no longer needed:
 ```yaml
   llm:
-    image: vllm/vllm-openai:v0.9.1
+    image: vllm/vllm-openai:v0.11.0
     [..]
 ```
 
diff --git a/docker-compose.yml b/docker-compose.yml
index c427acdc..72ea0187 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -99,7 +99,7 @@ services:
               capabilities: [gpu]
 
   llm:
-    image: vllm/vllm-openai:v0.9.1
+    image: vllm/vllm-openai:v0.11.0
     command:
       [
         # NOTE: Change the LLM here if you want.
diff --git a/dockerless/start_llm.sh b/dockerless/start_llm.sh
index bb8bc3bb..9830043d 100755
--- a/dockerless/start_llm.sh
+++ b/dockerless/start_llm.sh
@@ -2,7 +2,7 @@
 set -ex
 cd "$(dirname "$0")/.."
 
-uv tool run vllm@v0.9.1 serve \
+uv tool run vllm@v0.11.0 serve \
   --model=google/gemma-3-1b-it \
   --max-model-len=8192 \
   --dtype=bfloat16 \
diff --git a/swarm-deploy.yml b/swarm-deploy.yml
index 98361b03..a165da85 100644
--- a/swarm-deploy.yml
+++ b/swarm-deploy.yml
@@ -242,7 +242,7 @@ services:
           memory: 16G
 
   llm:
-    image: vllm/vllm-openai:v0.9.1
+    image: vllm/vllm-openai:v0.11.0
     command:
       [
         "--model=${KYUTAI_LLM_MODEL}",