lmcache

A LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios.

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install lmcache

Dependencies

  • None

Releases

Version Released Bullseye
Python 3.9
Bookworm
Python 3.11
Trixie
Python 3.13
Files
0.4.5 2026-05-15      
0.4.4 2026-04-23      
0.4.3 2026-04-07      
0.4.2 2026-03-18      
0.4.1 2026-03-12      
0.3.15 2026-03-02      
0.3.14 2026-02-17      
0.3.13 2026-01-29      
0.3.12 2026-01-05      
0.3.11 2025-12-15      
0.3.10.post2 2025-12-08      
0.3.10.post1 2025-12-05      
0.3.10 2025-11-28      
0.3.9.post2 2025-11-11      
0.3.9.post1 2025-11-06      
0.3.9 2025-10-29      
0.3.7 2025-09-29      
0.3.6 2025-09-15      
0.3.5 2025-08-29      
0.3.4 2025-08-25      
0.3.3 2025-08-03      
0.3.2 2025-07-15      
0.3.1.post1 2025-06-26      
0.3.1 2025-06-25      
0.3.0 2025-05-28      

Issues with this package?

Page last updated 2026-05-17 02:40:44 UTC