Popular repositories Loading

1. fp6_llm fp6_llm Public

   An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

   Cuda 181 15

2. NeuralNetworkRandomness NeuralNetworkRandomness Public

   Python 14

3. ReadingList ReadingList Public

   12

4. FSA FSA Public

   Webpage for FSA

   HTML 2

5. flash-llm flash-llm Public

   Forked from AlibabaResearch/flash-llm

   Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity

   Cuda 2

6. ConferenceTalk ConferenceTalk Public

   Conference talks given by FSA Lab, University of Sydney

   1