Stars
Accelerating MoE with IO and Tile-aware Optimizations
MoE training for Me and You and maybe other people
Provide with pre-build flash-attention package wheels on Linux and Windows platforms using GitHub Actions
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Pretraining data reconstruction scripts for Apertus
Distributed Compiler based on Triton for Parallel Systems
Development repository for the Triton language and compiler
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Pyrallis is a framework for structured configuration parsing from both cmd and files. Simply define your desired configuration structure as a dataclass and let pyrallis do the rest!
🔬 A fast, interactive web-based viewer for performance profiles.
An extremely fast Python type checker and language server, written in Rust.
Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch
Kimi K2 is the large language model series developed by Moonshot AI team
ROS 1 & 2 repos based on Mini Pupper legged robots from MangDang
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
An open-source AI agent that brings the power of Gemini directly into your terminal.
Data and tools for generating and inspecting OLMo pre-training data.
Knowledge transfer from high-resource to low-resource programming languages for Code LLMs
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
High level asynchronous concurrency and networking framework that works on top of either Trio or asyncio
Open-source framework for the research and development of foundation models.
Optimizing inference proxy for LLMs
Aidan Bench attempts to measure <big_model_smell> in LLMs.