diff --git a/docker-compose.yml b/docker-compose.yml index b0dfec8..1a7f554 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -9,7 +9,6 @@ services: - VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0 ipc: host command: > - vllm serve --model Qwen/Qwen2.5-14B-Instruct-AWQ --max-model-len 8192 --gpu-memory-utilization 0.97