Relaxed-System-Lab/HexGen
[ICML 2024] Serving LLMs on heterogeneous decentralized clusters.
This framework helps machine learning engineers and researchers serve large language models like Llama-2 on a cluster of different types of computers. It takes a trained Llama-2 model and a collection of computing resources, then optimizes how the model is split and run across those machines. The output is a highly efficient and coordinated system for responding to user requests for AI-generated text.
No commits in the last 6 months.
Use this if you need to deploy and run large language models on a distributed system with varying hardware capabilities, ensuring efficient request processing.
Not ideal if you are looking for a simple, single-machine inference solution or do not have experience managing distributed computing environments.
Stars
34
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
May 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Relaxed-System-Lab/HexGen"
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...