verl: Volcano Engine Reinforcement Learning for LLMs

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

🚀 Efficient implementations of state-of-the-art linear attention models

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Nano vLLM

Website URL

[ICLR 2025] Official PyTorch implementation of "Forgetting Transformer: Softmax Attention with a Forget Gate"

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

作曲编曲混音资料库