Pinned Loading

1. Kitty Kitty Public

   Algorithm-System Co-design: accurate and efficient 2-bit KV cache quantization for LLM Inference..

   Python 4 2

2. usyd-fsalab/fp6_llm usyd-fsalab/fp6_llm Public

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

   Cuda 276 22

3. AlibabaResearch/flash-llm AlibabaResearch/flash-llm Public

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

   Cuda 231 22

4. SpInfer SpInfer Public

   Forked from xxyux/SpInfer

   SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs

   Cuda

5. ComputerArchitectureLab ComputerArchitectureLab Public

   This repository is used to release the experimental assignments of Computer Architecture Course from USTC

   Verilog 39 14