v0.5.2-cu129

FerrisMind/omnivoice-rsv0.5.2-cu129Jul 22, 2026by github-actions[bot]

AI Summary

This release provides a binary wheel package for LMCache version 0.5.2 specifically compiled for CUDA 12.9, allowing users to install GPU-accelerated caching.

Key Highlights

CUDA 12.9 wheel for LMCache v0.5.2
Installation instructions provided
PyTorch compatible build

New Features

CUDA 12.9 wheel support

Full Release Notes

CUDA 12.9 wheel for LMCache v0.5.2.

```
VERSION=v0.5.2
uv pip install lmcache== \
  --extra-index-url https://download.pytorch.org/whl/cu129 \
  --find-links https://github.com/LMCache/LMCache/releases/expanded_assets/-cu129 \
  --index-strategy unsafe-best-match
```