A lightweight, user-friendly data-plane for LLM training.

PyTorch-native post-training at scale

A lightweight, local-first, and 🆓 experiment tracking library from Hugging Face 🤗

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

A Quirky Assortment of CuTe Kernels

Provider-agnostic, open-source evaluation infrastructure for language models

SkyRL: A Modular Full-stack RL Library for LLMs

Github mirror of trition-lang/triton repo.

An Open Source Toolkit For LLM Distillation

A Git-compatible VCS that is both simple and powerful

The HELMET Benchmark

Dion optimizer algorithm

Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with co…

Muon fsdp 2

Use Kimi latest model(kimi-k2-0711-preview) to drive your Claude Code.

H-Net: Hierarchical Network with Dynamic Chunking

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Standalone, relocatable Python app installs with uv

Letta is the platform for building stateful agents: open AI with advanced memory that can learn and self-improve over time.

Go ahead and axolotl questions

Jinja2 chat templates for popular LLM models

Official PyTorch implementation for "Large Language Diffusion Models"

Open-source unified multimodal model

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / veRL/ Swift / Ultra…

varlen hybrid mamba kernel