通过 vllm 部署 Qwen3.8-27B-FP8 模型

下载模型

Qwen3.8-27B-FP8 模型文件大小 30.89GB

使用 modelscope 下载模型

https://www.modelscope.cn/models/Qwen/Qwen3.8-27B-FP8

modelscope download --model Qwen/Qwen3.8-27B-FP8 README.md --local_dir /data/models/Qwen3.8-27B-FP8

启动 Qwen3.8-27B-FP8

https://recipes.vllm.ai/Qwen/Qwen3.8-27B?variant=fp8

CUDA_VISIBLE_DEVICES=0,1 vllm serve \
    /data/models/Qwen3.8-27B-FP8/ \
    --host 0.0.0.0 \
    --port 10304 \
    --tensor-parallel-size 2 \
    --gpu-memory-utilization 0.9 \
    --max-model-len 131072 \
    --enforce-eager \
    --enable-auto-tool-choice \
    --tool-call-parser qwen3_coder \
    --served-model-name Qwen3.8-27B-FP8

–enable-auto-tool-choice –tool-call-parser qwen3_coder 参数用于支持 tool call

在 claude code 中使用

~/.claude/setting.json

{
  "effortLevel": "xhigh",
  "enabledPlugins": {
    "gopls-lsp@claude-plugins-official": true
  },
  "env": {
    "ANTHROPIC_API_KEY": "dummy",
    "ANTHROPIC_BASE_URL": "http://192.168.110.28:10304",
    "ANTHROPIC_DEFAULT_FABLE_MODEL": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_FABLE_MODEL_NAME": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL_NAME": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_OPUS_MODEL_NAME": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "Qwen3.8-27B-FP8",
    "ANTHROPIC_DEFAULT_SONNET_MODEL_NAME": "Qwen3.8-27B-FP8",
    "API_TIMEOUT_MS": "3000000",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"
  },
  "model": "opus"
}