diff --git a/compose-vLLM.yaml b/compose-vLLM.yaml index ae6fbf5..4ff09db 100644 --- a/compose-vLLM.yaml +++ b/compose-vLLM.yaml @@ -21,12 +21,19 @@ services: - driver: nvidia count: all capabilities: [gpu] - command: > - --model Qwen/Qwen2.5-7B-Instruct-AWQ - --host 0.0.0.0 - --port 8000 - --gpu-memory-utilization 0.85 - --max-model-len 65536 - --hf-overrides {"rope_scaling":{"rope_type":"yarn","factor":2.0,"original_max_position_embeddings":32768}} - --enable-auto-tool-choice - --tool-call-parser hermes \ No newline at end of file + command: + - "--model" + - "Qwen/Qwen2.5-7B-Instruct-AWQ" + - "--host" + - "0.0.0.0" + - "--port" + - "8000" + - "--gpu-memory-utilization" + - "0.85" + - "--max-model-len" + - "65536" + - "--hf-overrides" + - '{"rope_scaling": {"rope_type": "yarn", "factor": 2.0, "original_max_position_embeddings": 32768}}' + - "--enable-auto-tool-choice" + - "--tool-call-parser" + - "hermes" \ No newline at end of file