Pinned Loading

1. LLM-Pruner LLM-Pruner Public

   [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

   Python 1.1k 132

2. DeepCache DeepCache Public

   [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

   Python 970 54

3. learning-to-cache learning-to-cache Public

   [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching

   Python 122 3

4. Awesome-Efficient-LLM Awesome-Efficient-LLM Public

   A curated list for Efficient Large Language Models

   Python 2k 168

5. dKV-Cache dKV-Cache Public

   [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models

   Python 135 12