Code Monkey home page Code Monkey logo

llm-continuous-batching-benchmarks's Introduction

LLM Continuous Batching

The code in this repo is a modified fork of the code use in the Anyscale blog How continuous batching enables 23x throughput in LLM inference while reducing p50 latency.

Getting Started

Environment Variables

The tesring parameters are mostly exposed through environment variables:

CUDA_MODULE_LOADING=LAZY
CUDA_VISIBLE_DEVICES=0,1,2,3
FORCE_CUDA=1
RAY_IGNORE_UNHANDLED_ERRORS=1

DEBIAN_FRONTEND=noninteractive
TENSOR_PARALLEL_SIZE=1
PIPELINE_PARALLEL_SIZE=1
SUBNET=172.42.6.0/24
BENCHMARK_IP=172.42.6.2
PORT=8008
RANDOM_PROMPT_LENS_MEAN=1500
RANDOM_PROMPT_LENS_RANGE=500
RANDOM_PROMPT_COUNT=5000
DISTRIBUTION=poisson
VARIABLE_RESPONSE_LENS_MEAN=100
VARIABLE_RESPONSE_LENS_RANGE=50
FIXED_MAX_TOKENS=150
QPS_RANGE=14
TRANSFORMERS_CACHE=/data/cache
TRANSFORMERS_MODEL=huggyllama/llama-30b
TOKENIZER_MODEL=huggyllama/llama-30b

Start Benchmark

  1. Build Docker Image: docker compose build
  2. Start Docker container: docker compose up

llm-continuous-batching-benchmarks's People

Contributors

cadedaniel avatar tuttlebr avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.