Popular repositories Loading

1. Flash-Sparse-Attention Flash-Sparse-Attention Public

   🚀🚀 Efficient implementations of Native Sparse Attention

   Python 603 15

2. multi-actor-data-selection multi-actor-data-selection Public

   This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.

   Python 49 3

3. HexGen HexGen Public

   [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.

   Python 36 3

4. HexiScale HexiScale Public

   Accommodating Large Language Model Training over Heterogeneous Environment.

   Python 32 10

5. HKUST-COMP6211J-2025fall HKUST-COMP6211J-2025fall Public

   24 1

6. UltraLLaDA UltraLLaDA Public

   We introduce UltraLLaDA , a scaled variant of LLaDA-8B-Base that extends the context length up to 128K tokens with light-weight post-training, enabling long-context comprehension and generation.

   Python 15