ekzhang

ekzhang/resin

🧱 Experimental library for building inference engines

267 stars 18 forks 267 watchers Python Apache License 2.0

cuda deepseek gpt-oss gpu inference inkling llm llm-serving

1 Open Issue Need Help Last updated: Oct 28, 2026

Open Issues Need Help

View All on GitHub

HTTP MAX_ACTIVE_REQUESTS is hard-coded to 128 7 days ago

good first issue

267

🧱 Experimental library for building inference engines

Python

#cuda#deepseek#gpt-oss#gpu#inference#inkling#llm#llm-serving