Lmcache
/All repositories
Overview
HEALTH SCORE
Healthy
82out of 100
Solid maintainer coverage and security posture. Development cadence keeps the score from reaching Excellent.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Healthy(82/100)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 1 day.
Bus factor
101 active maintainers currently have merge rights.
Company diversity
Contributors span 307 companies.
Project Achievements
LeaderboardsAbout
LMCache is a system designed to optimize the inference performance of large language models through intelligent caching mechanisms. It provides efficient key-value cache management to reduce redundant computations and improve throughput during LLM inference.
First commit
Software value
$17M
Tags
amd
cuda
fast
inference
kv-cache
llm
pytorch
rocm
speed
vllm
License(s)
Apache-2.0
Data sources
Git
GitHub