Skip to main content
buildradar
Sign in

IST-DASLab/marlin

@IST-DASLab

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

Stars
1,137
Forks
92
Language
Python
License
Apache-2.0
Last push
2 years ago
Pythonllmquantizationkernel4bit

No related intel yet

This repo has not appeared in any of the sources the radar tracks. The collector runs on a schedule — check back once it covers this repo.