v0.4.6-cu129

microsoft/markitdownv0.4.6-cu129May 29, 2026by github-actions[bot]

AI Summary

This release provides a CUDA 12.9 wheel for LMCache, enabling GPU acceleration for caching operations.

Key Highlights

CUDA 12.9 support for LMCache
Installation instructions provided for pip
Targeting LMCache version 0.4.6

Full Release Notes

CUDA 12.9 wheel for LMCache v0.4.6.

```
VERSION=v0.4.6
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
```