vllm启动模型的四种方式

前提：已安装好 vllm 库

一、单机单卡

1、方式一

 vllm serve facebook/opt-13b \ #模型名字或模型本地路径 （如果是模型名字，会默认从huggingface中下载）
     --dtype auto #类型默认auto

• 相关参数介绍（官方参数介绍链接）

usage: vllm serve [-h] [--host 主机名（可选）] [--port 端口号]
                  [--uvicorn-log-level {debug,info,warning,error,critical,trace}]
                  [--disable-uvicorn-access-log] [--allow-credentials]
                  [--allowed-origins ALLOWED_ORIGINS]
                  [--allowed-methods ALLOWED_METHODS]
                  [--allowed-headers ALLOWED_HEADERS] [--api-key API_KEY]
                  [--lora-modules LORA_MODULES [LORA_MODULES ...]]
                  [--prompt-adapters PROMPT_ADAPTERS [PROMPT_ADAPTERS ...]]
                  [--chat-template CHAT_TEMPLATE]
                  [--chat-template-content-format {auto,string,openai}]
                  [--response-role RESPONSE_ROLE] [--ssl-keyfile SSL_KEYFILE]
                  [--ssl-certfile SSL_CERTFILE] [--ssl-ca-certs SSL_CA_CERTS]
                  [--enable-ssl-refresh] [--ssl-cert-reqs SSL_CERT_REQS]
                  [--root-path ROOT_PATH] [--middleware MIDDLEWARE]
                  [--return-tokens-as-token-ids]
                  [--disable-frontend-multiprocessing]
                  [--enable-request-id-headers] [--enable-auto-tool-choice]
                  [--tool-call-parser {granite-20b-fc,granite,hermes,internlm,jamba,llama3_json,mistral,pythonic} or name registered in --tool-parser-plugin]
                  [--tool-parser-plugin TOOL_PARSER_PLUGIN] [--model MODEL]
                  [--task {auto,generate,embedding,embed,classify,score,reward,transcription}]
                  [--tokenizer TOKENIZER] [--hf-config-path HF_CONFIG_PATH]
                  [--skip-tokenizer-init] [--revision REVISION]
                  [--code-revision CODE_REVISION]
                  [--tokenizer-revision TOKENIZER_REVISION]
                  [--tokenizer-mode {auto,slow,mistral,custom}]
                  [--trust-remote-code]
                  [--allowed-local-media-path ALLOWED_LOCAL_MEDIA_PATH]
                  [--download-dir DOWNLOAD_DIR]
                  [--load-format {auto,pt,safetensors,npcache,dummy,tensorizer,sharded_state,gguf,bitsandbytes,mistral,runai_streamer,fastsafetensors}]
                  [--config-format {auto,hf,mistral}]
                  [--dtype {auto,half,float16,bfloat16,float,float32}]
                  [--kv-cache-dtype {auto,fp8,fp8_e5m2,fp8_e4m3}]
                  [--max-model-len MAX_MODEL_LEN]
                  [--guided-decoding-backend GUIDED_DECODING_BACKEND]
                  [--logits-processor-pattern LOGITS_PROCESSOR_PATTERN]
                  [--model-impl {auto,vllm,transformers}]
                  [--distributed-executor-backend {ray,mp,uni,external_launcher}]
                  [--pipeline-parallel-size PIPELINE_PARALLEL_SIZE]
                  [--tensor-parallel-size TENSOR_PARALLEL_SIZE]
                  [--data-parallel-size DATA_PARALLEL_SIZE]
                  [--enable-expert-parallel]
                  [--max-parallel-loading-workers MAX_PARALLEL_LOADING_WORKERS]
                  [--ray-workers-use-nsight] [--block-size {8,16,32,64,128}]
                  [--enable-prefix-caching | --no-enable-prefix-caching]
                  [--prefix-caching-hash-algo {builtin,sha256}]
                  [--disable-sliding-window] [--use-v2-block-manager]
                  [--num-lookahead-slots NUM_LOOKAHEAD_SLOTS] [--seed SEED]
                  [--swap-space SWAP_SPACE] [--cpu-offload-gb CPU_OFFLOAD_GB]
                  [--gpu-memory-utilization GPU_MEMORY_UTILIZATION]
                  [--num-gpu-blocks-override NUM_GPU_BLOCKS_OVERRIDE]
                  [--max-num-batched-tokens MAX_NUM_BATCHED_TOKENS]
                  [--max-num-partial-prefills MAX_NUM_PARTIAL_PREFILLS]
                  [--max-long-partial-prefills MAX_LONG_PARTIAL_PREFILLS]
                  [--long-prefill-token-threshold LONG_PREFILL_TOKEN_THRESHOLD]
                  [--max-num-seqs MAX_NUM_SEQS] [--max-logprobs MAX_LOGPROBS]
                  [--disable-log-stats]
                  [--quantization {aqlm,awq,deepspeedfp,tpu_int8,fp8,ptpc_fp8,fbgemm_fp8,modelopt,nvfp4,marlin,gguf,gptq_marlin_24,gptq_marlin,awq_marlin,gptq,compressed-tensors,bitsandbytes,qqq,hqq,experts_int8,neuron_quant,ipex,quark,moe_wna16,None}]
                  [--rope-scaling ROPE_SCALING] [--rope-theta ROPE_THETA]
                  [--hf-overrides HF_OVERRIDES] [--enforce-eager]
                  [--max-seq-len-to-capture MAX_SEQ_LEN_TO_CAPTURE]
                  [--disable-custom-all-reduce]
                  [--tokenizer-pool-size TOKENIZER_POOL_SIZE]
                  [--tokenizer-pool-type TOKENIZER_POOL_TYPE]
                  [--tokenizer-pool-extra-config TOKENIZER_POOL_EXTRA_CONFIG]
                  [--limit-mm-per-prompt LIMIT_MM_PER_PROMPT]
                  [--mm-processor-kwargs MM_PROCESSOR_KWARGS]
                  [--disable-mm-preprocessor-cache] [--enable-lora]
                  [--enable-lora-bias] [--max-loras MAX_LORAS]
                  [--max-lora-rank MAX_LORA_RANK]
                  [--lora-extra-vocab-size LORA_EXTRA_VOCAB_SIZE]
                  [--lora-dtype {auto,float16,bfloat16}]
                  [--long-lora-scaling-factors LONG_LORA_SCALING_FACTORS]
                  [--max-cpu-loras MAX_CPU_LORAS] [--fully-sharded-loras]
                  [--enable-prompt-adapter]
                  [--max-prompt-adapters MAX_PROMPT_ADAPTERS]
                  [--max-prompt-adapter-token MAX_PROMPT_ADAPTER_TOKEN]
                  [--device {auto,cuda,neuron,cpu,tpu,xpu,hpu}]
                  [--num-scheduler-steps NUM_SCHEDULER_STEPS]
                  [--use-tqdm-on-load | --no-use-tqdm-on-load]
                  [--multi-step-stream-outputs [MULTI_STEP_STREAM_OUTPUTS]]
                  [--scheduler-delay-factor SCHEDULER_DELAY_FACTOR]
                  [--enable-chunked-prefill [ENABLE_CHUNKED_PREFILL]]
                  [--speculative-config SPECULATIVE_CONFIG]
                  [--speculative-model SPECULATIVE_MODEL]
                  [--speculative-model-quantization {aqlm,awq,deepspeedfp,tpu_int8,fp8,ptpc_fp8,fbgemm_fp8,modelopt,nvfp4,marlin,gguf,gptq_marlin_24,gptq_marlin,awq_marlin,gptq,compressed-tensors,bitsandbytes,qqq,hqq,experts_int8,neuron_quant,ipex,quark,moe_wna16,None}]
                  [--num-speculative-tokens NUM_SPECULATIVE_TOKENS]
                  [--speculative-disable-mqa-scorer]
                  [--speculative-draft-tensor-parallel-size SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE]
                  [--speculative-max-model-len SPECULATIVE_MAX_MODEL_LEN]
                  [--speculative-disable-by-batch-size SPECULATIVE_DISABLE_BY_BATCH_SIZE]
                  [--ngram-prompt-lookup-max NGRAM_PROMPT_LOOKUP_MAX]
                  [--ngram-prompt-lookup-min NGRAM_PROMPT_LOOKUP_MIN]
                  [--spec-decoding-acceptance-method {rejection_sampler,typical_acceptance_sampler}]
                  [--typical-acceptance-sampler-posterior-threshold TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD]
                  [--typical-acceptance-sampler-posterior-alpha TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA]
                  [--disable-logprobs-during-spec-decoding [DISABLE_LOGPROBS_DURING_SPEC_DECODING]]
                  [--model-loader-extra-config MODEL_LOADER_EXTRA_CONFIG]
                  [--ignore-patterns IGNORE_PATTERNS]
                  [--preemption-mode PREEMPTION_MODE]
                  [--served-model-name SERVED_MODEL_NAME [SERVED_MODEL_NAME ...]]
                  [--qlora-adapter-name-or-path QLORA_ADAPTER_NAME_OR_PATH]
                  [--show-hidden-metrics-for-version SHOW_HIDDEN_METRICS_FOR_VERSION]
                  [--otlp-traces-endpoint OTLP_TRACES_ENDPOINT]
                  [--collect-detailed-traces COLLECT_DETAILED_TRACES]
                  [--disable-async-output-proc]
                  [--scheduling-policy {fcfs,priority}]
                  [--scheduler-cls SCHEDULER_CLS]
                  [--override-neuron-config OVERRIDE_NEURON_CONFIG]
                  [--override-pooler-config OVERRIDE_POOLER_CONFIG]
                  [--compilation-config COMPILATION_CONFIG]
                  [--kv-transfer-config KV_TRANSFER_CONFIG]
                  [--worker-cls WORKER_CLS]
                  [--worker-extension-cls WORKER_EXTENSION_CLS]
                  [--generation-config GENERATION_CONFIG]
                  [--override-generation-config OVERRIDE_GENERATION_CONFIG]
                  [--enable-sleep-mode] [--calculate-kv-scales]
                  [--additional-config ADDITIONAL_CONFIG] [--enable-reasoning]
                  [--reasoning-parser {deepseek_r1,granite}]
                  [--disable-cascade-attn] [--disable-log-requests]
                  [--max-log-len MAX_LOG_LEN] [--disable-fastapi-docs]
                  [--enable-prompt-tokens-details]
                  [--enable-server-load-tracking]

2、方式二

python -m vllm.entrypoints.openai.api_server --model ./path/deepseek_model #模型名字或模型本地路径 （如果是模型名字，会默认从huggingface中下载）
 --port 8000 #启动指定的端口号

二、单机多卡

1、方式一

• 只启动tensor-parallel-size，值可以等于GPU的数量

 vllm serve facebook/opt-13b \
     --tensor-parallel-size 4

• 同时使用 tensor-parallel-size 和 pipeline-parallel-size，两者之积 = GPU数量

#GPU 数量为 8
 vllm serve gpt2 \
     --tensor-parallel-size 4 \
     --pipeline-parallel-size 2

2、方式二

CUDA_VISIBLE_DEVICES=0,1 python -m vllm.entrypoints.openai.api_server 
--model ./path/model --port 8000 --tensor-parallel-size 2

• CUDA_VISIBLE_DEVICES=0,1 表示让程序看到设备 ID 为 0 和 1 的两个 GPU
• –tensor-parallel-size 2 表示使用 2 个 GPU 进行张量并行计算，加速推理过程。（当只使用tensor-parallel-size时，值可以等于GPU的数量；若同时使用 tensor-parallel-size 和 pipeline-parallel-size时，两者之积 = GPU数量）
• –model 指定模型文件路径
• –port 可自定义端口。