Popular repositories

1. Atom Atom Public

   Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

   Cuda 177 13

2. fiddler fiddler Public

   Fast Inference of MoE Models with CPU-GPU Orchestration

   Python 139 15

3. lapidary lapidary Public

   Creating beautiful gem5 simulations

   C++ 43 14

4. DMon-AE DMon-AE Public

   DMon Prototype for OSDI 2021 Artifact Evaluation

   C++ 20 1

5. optimus-hypervisor optimus-hypervisor Public

   18

6. huron huron Public

   A false sharing detection and repair tool

   C++ 12 2