Popular repositories Loading

1. gpu-embedding-cache gpu-embedding-cache Public

   Two-tier GPU embedding cache with LRU eviction for large-scale inference (C++/CUDA + PyTorch)

   Cuda 1

2. embedding_cache_torchrec embedding_cache_torchrec Public

   High-performance inference embedding lookup using TorchRec + FBGEMM with CPU-resident embeddings and GPU UVM caching

   Python 1

3. nv-embedding-cache nv-embedding-cache Public

   Two-tier embedding cache for PyTorch inference: CPU pinned memory + GPU HBM LRU cache. Tested at 200GB scale on H100.

   Python 1

4. BigGame BigGame Public

5. Spoon-Knife Spoon-Knife Public

   Forked from octocat/Spoon-Knife

   This repo is for demonstration purposes only. Comments and issues may or may not be responded to.

6. main main Public

   Forked from exvim/main

   This is the main repository for exVim!

   Vim Script