Tool profile

NVIDIA/kvpress

stable

LLM KV cache compression made easy

inferencekv-cachekv-cache-compressionlarge-language-modelsllmlong-contextpythonpytorch

Velocity score

0.78/ 10

[STARS]

1.1k

[FORKS]

145

[CONTRIBUTORS]

[LAST_COMMIT]

10d ago

Score breakdown

693/ 1000

inference · NVIDIA/kvpress

Velocity50%

Adoption30%

Maintenance15%

Community5%

[CODE_GROWTH]

829

[INSTALL_VEL]

498

[ACTIVITY]

594

[COMMUNITY_SIGNAL]

808

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).