Source: vLLM docs: Engine Arguments
Official reference of vLLM engine/server flags and their defaults.
Contents
- What: official documentation (latest, read 2026-11-14)
- Author: vLLM project
- Date: 2026-11-14 (accessed)
- Original: vLLM docs: Engine Arguments
Summary
The full list of flags accepted by vllm serve and the LLM class, grouped by model, cache, parallel, scheduler, LoRA and compilation configuration.
Key claims
--gpu-memory-utilization: fraction of GPU memory the instance may use; default 0.92 (1.0 with an extensible KV cache).--max-model-lendefaults from the model config;--dtype autokeeps BF16 for BF16 models and uses FP16 for FP16/FP32 ones;--kv-cache-dtype auto.--enforce-eager(default off) disables CUDA graphs and torch.compile.--tensor-parallel-size,--pipeline-parallel-size,--data-parallel-sizedefault to 1;--enable-expert-parallel(default off) uses EP instead of TP for MoE layers;--decode-context-parallel-sizeand--prefill-context-parallel-sizeshard the KV cache / prefill across ranks.--async-schedulingoverlaps CPU scheduling with GPU work.--cpu-offload-gb(weights to CPU, default 0) and--kv-offloading-size(CPU KV buffer, off by default).- LoRA:
--enable-lora,--max-loras(default 1 per batch),--max-lora-rank(default 16). --seeddefault 0;--trust-remote-codedefault off;--served-model-namedefaults to the model path.