Skip to content
#

gpu-runtime

Here are 6 public repositories matching this topic...

Language: All
Filter by language

CuTileForge v3.0.0: Native tile-fusion compiler & universal quantization engine on NVIDIA CuTile. Zero-ATen CUDA-graph decode at 172 tok/s, 2,377 tok/s batch serving, 13 model families, 70B hybrid on a single 32 GB GPU (sm_89 ↔ sm_120).

  • Updated Nov 21, 2026
  • Python

Add this topic to your repo

To associate your repository with the gpu-runtime topic, visit your repo's landing page and select "manage topics."

Learn more