X-rayLaser/DistributedLLM
Run LLM inference by spliting models into parts and hosting each part on a separate machine. Project is no longer maintained.
This project helps you run large language models (LLMs) even if they are too big for a single computer's memory. You provide your LLM and a simple configuration, and the system splits the model across multiple machines and manages the connections. This is for users who want to run powerful LLMs without needing extremely high-end, single-machine hardware.
No commits in the last 6 months.
Use this if you need to run large LLaMA v1 or OpenLLaMA v1 models for basic text generation but your models don't fit on a single machine's RAM.
Not ideal if you need to work with LLaMA v2, OpenLLaMA v2, or chat-specific models, or if you require GPU support as these features are not yet implemented.
Stars
8
Forks
—
Language
Python
License
MIT
Category
Last pushed
Sep 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/X-rayLaser/DistributedLLM"
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...