Pinned Loading

1. LatencySensitiveBench LatencySensitiveBench Public

   First Latency-Aware Competitive LLM Agent Benchmark

   Python 20 1

2. opengear-project/GEAR opengear-project/GEAR Public

   GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM

   Python 165 16

3. torchanalyse torchanalyse Public

   A pytorch model profiler with information about macs, energy and e.t.c

   Python 13 1

4. Lyken17/pytorch-OpCounter Lyken17/pytorch-OpCounter Public

   Count the MACs / FLOPs of your PyTorch model.

   Python 5k 534

5. haokang-timmy.github.io haokang-timmy.github.io Public

   Forked from zxjcarrot/zxjcarrot.github.io

   Personal Website(forked from Xinjing)

   HTML

6. Epipe Epipe Public

   A gpipe test

   Python 1 1