Popular repositories Loading

1. FastVideo FastVideo Public

   A unified inference and post-training framework for accelerated video generation.

   Python 4.1k 422

2. LookaheadDecoding LookaheadDecoding Public

   [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

   Python 1.3k 83

3. Consistency_LLM Consistency_LLM Public

   [ICML 2024] CLLMs: Consistency Large Language Models

   Python 415 23

4. Dynasor Dynasor Public

   [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.

   Python 232 32

5. JetSpec JetSpec Public

   JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting

   Python 177 7

6. d3LLM d3LLM Public

   [ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀

   Python 149 10