Skip to main content

A lightweight LLM inference framework

Project description

light-llm-hp - 轻量级 LLM 推理框架

在 CPU 上运行的简化推理框架,支持 REST API 服务。

快速开始

from hllm import HLLM

# 初始化模型
model = HLLM(model_path="microsoft/Phi-3-mini-4k-instruct", device="cpu")

# 生成文本
result = model.generate("Write a short story about a robot.")
print(result)

REST API 服务

安装 API 依赖

pip install light-llm-hp[api]

启动服务

from hllm import HLLM
from hllm.server import Server

model = HLLM(model_path="./TinyLlama-1.1B-Chat-v1.0", device="cpu")
server = Server(model, host="0.0.0.0", port=8000)
server.start()

或通过命令行:

python -m hllm.server --model ./TinyLlama-1.1B-Chat-v1.0 --port 8000

API 端点

端点 方法 说明
/health GET 健康检查
/models GET 模型信息
/generate POST 文本生成
/chat POST 对话生成
/generate/stream POST 流式生成 (SSE)

使用客户端

from hllm.client import HLLMClient

client = HLLMClient("http://localhost:8000")

# 生成文本
response = client.generate("Hello, how are you?")
print(response.text)

# 对话
response = client.chat([
    {"role": "user", "content": "What is AI?"}
])
print(response.message.content)

# 流式生成
for chunk in client.generate_stream("Tell me a story"):
    print(chunk.token, end="", flush=True)

详细 API 文档见 docs/api.md

目录结构

hllm/
├── hllm/              # 核心模块
│   ├── __init__.py
│   ├── model.py       # 模型加载与推理
│   ├── tokenizer.py   # 分词器封装
│   ├── generate.py    # 生成逻辑
│   ├── server.py      # REST API 服务端
│   └── client.py      # REST API 客户端
├── tests/             # 测试
├── examples/          # 示例
└── docs/              # 文档

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

light_llm_hp-0.3.0-py3-none-any.whl (12.7 kB view details)

Uploaded Python 3

File details

Details for the file light_llm_hp-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: light_llm_hp-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 12.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for light_llm_hp-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4f428f35b0e8e94de54d6ac52d459523d2a3597206cb3bf6b29abb85c5e9f8aa
MD5 ab8a4c725c9dd80dd4e241fa4168faf5
BLAKE2b-256 4cd7235ea50f40deaae29e3949fbe709333ef74eadf4eaa315800b31b6ae6323

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page