diff --git a/docker-compose.yml b/docker-compose.yml index fc801c1..b0dfec8 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -10,7 +10,7 @@ services: ipc: host command: > vllm serve - Qwen/Qwen2.5-14B-Instruct-AWQ + --model Qwen/Qwen2.5-14B-Instruct-AWQ --max-model-len 8192 --gpu-memory-utilization 0.97 ports: