#
Starred repositories
Open-source Multi-agent Poster Generation from Papers
llm-d is a Kubernetes-native high-performance distributed LLM inference framework
No fortress, purely open ground. OpenManus is Coming.
📚LeetCUDA: 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.
Disaggregated serving system for Large Language Models (LLMs).
Minimal reproduction of DeepSeek R1-Zero
High performance Transformer implementation in C++.
Curated collection of papers in machine learning systems
Deadlocks? Detect where your threads hang in Python with one import.
Dynamic resources changes for multi-dimensional parallelism training
Serverless LLM Serving for Everyone.
LLM Serving Performance Evaluation Harness
SGLang is a fast serving framework for large language models and vision language models.
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
High-speed Large Language Model Serving for Local Deployment
An Autonomous LLM Agent for Complex Task Solving
A modular graph-based Retrieval-Augmented Generation (RAG) system
Ongoing research training transformer models at scale
🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents