0xSero/turboquant

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

1.8k
Stars
199
Forks
0.0
Radar Score
Declining
Momentum

Scoring Breakdown

Impact0.0
Velocity0.0
Health0.0

Growth Metrics

7-Day Stars
+0
30-Day Stars
+0
Acceleration
x
Language
Python

Why it ranks

Momentum is cooling relative to the rest of the index.

LLM Frameworks · inference engine
View on GitHub