LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Python

LMCache

Supercharge Your LLM with the Fastest KV Cache Layer

PythonEmerging

Stars

—

Forks

—

Contributors

8

Last push

24d ago

Recent commits

Latest commits.

fix: prevent TypeError crash when streaming response has zero visible content (#3258)
bd713b5weizhoublue24d ago
[Bugfix] Fix 0-hit async lookup when use_layerwise=true (#3252)
1b8785aKihwan Kim24d ago
[hipFile]: Add cufile-python compatible shim layer to use AMD's hipFile package. (#3115)
9a34979Riley Dixon24d ago
[CI] smoke-test container images before pushing (#3358)
370cf94deng451e24d ago
[Fix]: Skip unpin for non-pinned objects in cleanup_memory_objs (#3385)
62bb37dZhengfei He24d ago

[Operator]: Force external LMCache MP connector path (#3393)

956b7bdSamuel Shen24d ago

[Fix] Change pinned pointer allocations in non-CUDA equivalents to be page-aligned for O_DIRECT (#3191)

4bdcb5cZhengfei He24d ago

docs: daily drift check — multi-process mode (2026-05-21) (#3361)

ec4dbe1Yihua Cheng24d ago

Top contributors

Builders behind this project.