Use more recent version of vllm

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
     [..]
 ```
 

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.

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 \

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}",