Spaces:
No application file
No application file
File size: 3,693 Bytes
bbb2a4d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# <h1 align=\"center\"><font color=\"red\">Introdução ao uso do vLLM</font></h1>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<font color=\"pink\">Senior Data Scientist.: Dr. Eddy Giusepe Chirinos Isidro</font>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Link de estudo:\n",
"\n",
"* [vllm-project](https://github.com/vllm-project/vllm?tab=readme-ov-file)\n",
"\n",
"* [vllm: quickstart](https://docs.vllm.ai/en/latest/getting_started/quickstart.html)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<font color=\"orange\">`vLLM` é uma biblioteca rápida e fácil de usar para inferência e serviço de `LLM`.</font>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"<font color=\"orange\">Você deve executar o seguinte comando no terminal (deixa ele rodando como você faz no `ollama`):</font>\n",
"\n",
"```bash\n",
"vllm serve Qwen/Qwen2.5-1.5B-Instruct \n",
"```"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from openai import OpenAI\n",
"\n",
"# Modifique o OpenAI's API key e API base para usar o servidor API do vLLM:\n",
"openai_api_key = \"EMPTY\"\n",
"openai_api_base = \"http://localhost:8000/v1\"\n",
"\n",
"client = OpenAI(\n",
" api_key=openai_api_key,\n",
" base_url=openai_api_base,\n",
")\n",
"completion = client.completions.create(model=\"Qwen/Qwen2.5-1.5B-Instruct\",\n",
" prompt=\"San Francisco é uma\")\n",
"\n",
"print(\"Completion result:\", completion.choices[0].text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from openai import OpenAI\n",
"\n",
"# Modifique o OpenAI's API key e API base para usar o servidor API do vLLM:\n",
"openai_api_key = \"EMPTY\"\n",
"openai_api_base = \"http://localhost:8000/v1\"\n",
"\n",
"client = OpenAI(\n",
" api_key=openai_api_key,\n",
" base_url=openai_api_base,\n",
")\n",
"\n",
"chat_response = client.chat.completions.create(model=\"Qwen/Qwen2.5-1.5B-Instruct\",\n",
" messages=[{\"role\": \"system\", \"content\": \"Você é um assistente útil.\"},\n",
" {\"role\": \"user\", \"content\": \"Conta para mim uma piada.\"},\n",
" ]\n",
" )\n",
"\n",
"print(\"Chat response:\", chat_response.choices[0].message.content)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|