Lists (4)
Stars
Building the Virtuous Cycle for AI-driven LLM Systems
How to ensure correctness and ship LLM generated kernels in PyTorch
A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention
A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
nanobind: tiny and efficient C++/Python bindings
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >70% on SWE-bench verified!
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention
"RAG-Anything: All-in-One RAG Framework"
slime is an LLM post-training framework for RL Scaling.
🚀 Efficient implementations of state-of-the-art linear attention models
Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.
[NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
[NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.
Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism (NIPS'25)
[OSDI'25] QiMeng-Xpiler: Transcompiling Tensor Programs for Deep Learning Systems with a Neural-Symbolic Approach
Source code repository for ASPLOS '25 paper "Syno: Structured Synthesis for Neural Operators"
RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
Run the latest vscode-server on RHEL/CentOS 7!
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Model Context Protocol Servers
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.