Stars
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A simple, fast and robust program-aware agentic inference system.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
A useful plugin for the ChatGPT web platform, focusing on long conversation browsing, exporting, searching, prompt management, and timeline navigation. 🚀||优化ChatGPT长会话卡顿，聊天记录一键导出，消息搜索跳转，会话管理，prompt…
Resource-adaptive cluster scheduler for deep learning training.
[NeurIPS 2025] A Graph-based LLM Framework for Real-world SE Tasks
[EMNLP 2025] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward
[ACL 2025] Graph-guided agentic framework for code localization https://arxiv.org/abs/2503.09089
[ACL 2025] Graph Aligned Large Language Models for Improved Source Code Understanding
Serverless LLM Serving for Everyone.
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
An incremental parsing system for programming tools
A simple, easy-to-hack GraphRAG implementation
Extract and combine multiple source code views using tree-sitter
A robust streaming log template miner based on the Drain algorithm
[FSE'26, WWW'25, ASE'24] RCAEval: A Benchmark for Root Cause Analysis.
[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?
The published dataset of AIOps Challenge 2020
cluster data collected from production clusters in Alibaba for cluster management research
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
Time series forecasting with PyTorch
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"