GitHub Trending

deepseek-ai/DeepEP — DeepEP: an efficient expert-parallel communication library

27 sec read486 views0 listens

9,312 stars | 1,180 forks | Cuda

DeepEP: an efficient expert-parallel communication library

What it does

DeepEP is a communication library designed for Mixture-of-Experts models, offering high-throughput and low-latency GPU kernels that enhance both training and inference performance in large-scale AI applications.

Why it matters: Revolutionize your Mixture-of-Experts model with DeepEP, the cutting-edge communication library for high-throughput and low-latency GPU kernels. #AI

View on GitHub

Trending today with 29 new stars

Want to create content about this repo? Use Nemati AI tools to generate articles, tutorials, and social posts.

You Might Like

GitHub Trending2 days ago34 sec read

vllm-project/vllm — A high-throughput and memory-efficient inference and serving engine for LLMs

94,317 stars | 23,654 forks | Python A high-throughput and memory-efficient inference and serving engine for LLMs What it does vLLM is a high-throughput and memory-efficient inference and serving engine for Large Language Models (LLMs). It's designed...

Ali Nemati

GitHub TrendingSep 336 sec read

magnitudedev/magnitude — Open source inference server that runs the best local models for your hardware,

1,752 stars | 134 forks | TypeScript Open source inference server that runs the best local models for your hardware, plugged into the agent you already use. Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline. What it d...

Ali Nemati

GitHub TrendingSep 231 sec read

superlinked/sie — Open-source inference server and production cluster for all the models your agen

2,956 stars | 297 forks | Python Open-source inference server and production cluster for all the models your agent needs. What it does SIE is an open-source inference engine designed to serve multiple machine learning models for agent tasks through a...

Ali Nemati