diff --git a/docker-compose.yml b/docker-compose.yml
index a925ad4..51f82f4 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -20,6 +20,7 @@ services:
       --n-gpu-layers ${LLAMA_GPU_LAYERS:-999}
       --ctx-size ${LLAMA_CTX_SIZE:-131072}
       --parallel ${LLAMA_PARALLEL:-2}
+      --flash-attn on
       --jinja
     # No published host port: llama-server is reached only via the omniroute
     # gateway on the ai-stack docker network now — see issue #15. Its