Alberto-Codes/turboquant-vllm

TurboQuant KV cache compression plugin for vLLM — asymmetric K/V, 8 models validated, consumer GPUs

49

Stars

6

Forks

25.6

Radar Score

Stable

Momentum

Scoring Breakdown

Impact18.0

Velocity31.1

Health30.1

Growth Metrics

7-Day Stars

+0

30-Day Stars

+0

Acceleration

x

Language

Python

Why it ranks

Modest but positive momentum.

LLM FrameworksTop 91% globally