Pinned Loading

1. NPU-architecture-modeling NPU-architecture-modeling Public

   C++/SystemC NPU models: quantized and compressed inference, stateful FP16/BF16 transformers, multicore scheduling, DVFS, TLM and live observability

   Python

2. google/highway google/highway Public

   Performance-portable, length-agnostic SIMD with runtime dispatch

   C++ 6k 498

3. google/XNNPACK google/XNNPACK Public

   High-efficiency floating-point neural network inference operators for mobile, server, and Web

   C 2.5k 590

4. NVIDIA/warp NVIDIA/warp Public

   A Python framework for GPU-accelerated simulation, robotics, and machine learning.

   Python 7.3k 692

5. NVIDIA/nccl NVIDIA/nccl Public

   Optimized primitives for collective multi-GPU communication

   C++ 5.2k 1.5k

6. google/ruy google/ruy Public

   C++ 326 97