微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and supp…

Mamba SSM architecture

Twinkle✨: Training workbench to make your model glow.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

slime is an LLM post-training framework for RL Scaling.

Puzzles for learning Triton

DLRover: An Automatic Distributed Deep Learning System

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, P…