Popular repositories Loading

1. Nanoflow Nanoflow Public

   A throughput-oriented high-performance serving framework for LLMs

   Jupyter Notebook 826 37

2. Atom Atom Public

   [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

   Cuda 310 27

3. fiddler fiddler Public

   [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration

   Python 213 23

4. LiteASR LiteASR Public

   LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation

   Python 109 5

5. lapidary lapidary Public archive

   Creating beautiful gem5 simulations

   C++ 49 13

6. DMon-AE DMon-AE Public

   DMon Prototype for OSDI 2021 Artifact Evaluation

   C++ 22 1