diff --git a/docker-compose.yml b/docker-compose.yml index 1a7f554..dcf1d38 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -11,7 +11,7 @@ services: command: > --model Qwen/Qwen2.5-14B-Instruct-AWQ --max-model-len 8192 - --gpu-memory-utilization 0.97 + --gpu-memory-utilization 0.95 ports: - "8000:8000" volumes: