Pinned Loading

1. hpcaitech/ColossalAI hpcaitech/ColossalAI Public

   Making large AI models cheaper, faster and more accessible

   Python 41.2k 4.5k

2. xdit-project/xDiT xdit-project/xDiT Public

   xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

   Python 2.3k 274

3. Tencent/TurboTransformers Tencent/TurboTransformers Public

   a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

   C++ 1.5k 206

4. LLMSpeculativeSampling LLMSpeculativeSampling Public

   Fast inference from large lauguage models via speculative decoding

   Python 828 84

5. Tencent/PatrickStar Tencent/PatrickStar Public

   PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

   Python 767 58

6. long-context-attention long-context-attention Public

   USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

   Python 571 66