OnlyTerp/turboquant
First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression with near-zero quality loss.
80
Stars
11
Forks
29.4
Radar Score
Stable
Momentum
Scoring Breakdown
Impact29.9
Velocity24.0
Health36.4
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python