IST-DASLab/marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

1.2k

Stars

95

Forks

46.3

Radar Score

Stable

Momentum

Scoring Breakdown

Impact67.4

Velocity30.2

Health35.0

Growth Metrics

7-Day Stars

+0

30-Day Stars

+0

Acceleration

x

Language

Python

Why it ranks

Modest but positive momentum.

LLM Frameworks · inference engineTop 48% globally