guoqingbao / candle-vllm Goto Github PK

Efficient, easy-to-use platform for inference and serving local LLMs including an OpenAI compatible API server.

• OpenAI compatible API server provided for serving LLMs.
• Highly extensible trait-based system to allow rapid implementation of new module pipelines,
• Streaming support in generation.
• Efficient management of key-value cache with PagedAttention.
• Continuous batching.

Currently, candle-vllm supports chat serving for the following models.

See this folder for some examples.

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
sudo apt install libssl-dev
sudo apt install pkg-config
git clone [email protected]:EricLBuehler/candle-vllm.git
cd candle-vllm
cargo run --release -- --port 2000 --weight-path /home/llama2_7b/ llama --repeat-last-n 64

You may also run specific model using huggingface model-id, e.g.,

cargo run --release -- --port 2000 --model-id meta-llama/Llama-2-7b-chat-hf llama --repeat-last-n 64

Install ChatUI and its dependencies:

git clone [email protected]:guoqingbao/candle-vllm-demo.git
cd candle-vllm-demo
apt install npm #install npm if needed
npm install n -g #update node js if needed
n stable #update node js if needed
npm i -g pnpm #install pnpm manager
pnpm install #install ChatUI dependencies

Launching the ChatUI:

pnpm run dev # run the ChatUI

curl -X POST "http://127.0.0.1:2000/v1/chat/completions" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -d '{
           "model": "llama7b",
           "messages": [
               {"role": "user", "content": "Explain how to best learn Rust."}
           ],
           "temperature": 0.7,
          "max_tokens": 128,
          "stop": {"Single":"</s>"}
       }'

Sample response:

{"id":"cmpl-53092967-c9cf-40e0-ae26-d7ac786d59e8","choices":[{"message":{"content":" Learning any programming language requires a combination of theory, practice, and dedication. Here are some steps and resources to help you learn Rust effectively:\n\n1. Start with the basics:\n\t* Understand the syntax and basic structure of Rust programs.\n\t* Learn about variables, data types, loops, and control structures.\n\t* Familiarize yourself with Rust's ownership system and borrowing mechanism.\n2. Read the Rust book:\n\t* The Rust book is an official resource that provides a comprehensive introduction to the language.\n\t* It covers topics such","role":"[INST]"},"finish_reason":"length","index":0,"logprobs":null}],"created":1718784498,"model":"llama7b","object":"chat.completion","usage":{"completion_tokens":129,"prompt_tokens":29,"total_tokens":158}}

In your terminal, install the openai Python package by running pip install openai. I use version 1.3.5.

Then, create a new Python file and write the following code:

import openai

openai.api_key = "EMPTY"

openai.base_url = "http://localhost:2000/v1/"

completion = openai.chat.completions.create(
    model="llama",
    messages=[
        {
            "role": "user",
            "content": "Explain how to best learn Rust.",
        },
    ],
    max_tokens = 64,
)
print(completion.choices[0].message.content)

After the candle-vllm service is running, run the Python script and enjoy efficient inference with an OpenAI compatible API server!

For general configuration help, run cargo run -- --help.

For model-specific help, run cargo run -- --port 2000 <MODEL_TYPE> --help

For local model weights, run cargo run --release -- --port 2000 --weight-path /home/llama2_7b/ llama --repeat-last-n 64, change the path when needed.

MODEL_TYPE = ["llama", "mistral", "phi2", "phi3", "qwen2", "gemma", "yi", "stable-lm"]

WEIGHT_FILE_PATH = Corresponding weight path for the given model type

cargo run --release -- --port 2000 --weight-path <WEIGHT_FILE_PATH> <MODEL_TYPE> --repeat-last-n 64

or

MODEL_ID = Huggingface model id

cargo run --release -- --port 2000 --model-id <MODEL_ID> <MODEL_TYPE> --repeat-last-n 64

For kvcache configuration, set kvcache_mem_cpu and kvcache_mem_gpu, default 4GB CPU memory and 4GB GPU memory for kvcache.

For chat history settings, set record_conversation to true to let candle-vllm remember chat history. By default, candle-vllm does not record chat history; instead, the client sends both the messages and the contextual history to candle-vllm. If record_conversation is set to true, the client sends only new chat messages to candle-vllm, and candle-vllm is responsible for recording the previous chat messages. However, this approach requires per-session chat recording, which is not yet implemented, so the default approach record_conversation=false is recommended.

For chat streaming, the stream flag in chat request need to be set to True.

You may supply penalty and temperature to the model to prevent potential repetitions, for example:

cargo run --release -- --port 2000 --weight-path /home/mistral_7b/ mistral --repeat-last-n 32 --penalty 1.1 --temperature 0.8

--max-gen-tokens parameter is used to control the maximum output tokens per chat response. The value will be set to 1/5 of max_sequence_len by default.

Installing candle-vllm is as simple as the following steps. If you have any problems, please create an issue.

The following features are planned to be implemented, but contributions are especially welcome:

• Sampling methods:
  • Beam search (huggingface/candle#1319)
• More pipelines (from candle-transformers)

• Python implementation: vllm-project
• vllm paper