modelize-ai/LLM-Inference-Deployment-Tutorial
Tutorial for LLM developers about engine design, service deployment, evaluation/benchmark, etc. Provide a C/S style optimized LLM inference engine.
This project provides an advanced tutorial and an optimized, open-source inference engine for Large Language Models (LLMs) specifically designed for single-GPU deployment. It helps LLM developers understand and implement efficient deployment strategies, going from raw LLM weights to a functional, client-server based inference service. The primary users are engineers responsible for deploying and optimizing LLMs in production environments.
No commits in the last 6 months.
Use this if you are an LLM developer looking to understand the inner workings and optimize the performance of a single-GPU LLM inference engine in a production setting.
Not ideal if you need multi-GPU inference, streaming support, or have models other than Llama v1/v2 (excluding 70B), or if your focus isn't on engine design but rather on using a fully-featured, off-the-shelf solution.
Stars
19
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/modelize-ai/LLM-Inference-Deployment-Tutorial"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
sgl-project/sglang
SGLang is a high-performance serving framework for large language models and multimodal models.
alibaba/MNN
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering...
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source,...
tensorzero/tensorzero
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM...