awesome-repositories.comBlog

© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com

MCP Blog Curated searches Sitemap Privacy Terms

Marlin | Awesome Repository

IST-DASLabmarlin

0

View on GitHub↗

1,088 stars·88 forks·Python·Apache-2.0·0 views

Marlin

Features

Tensor Core Optimization - Mixed-precision kernels for parallel autoregressive inference on large models.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

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