flashinfer-cubin has 3M monthly downloads and 6K GitHub stars. Version 0.6.13 supports Python 3.8+, first published in 2025.
It is actively maintained under a permissive license, last released in Jun 2026.
It is used by 8 tracked packages, including sglang, vllm and megatron-bridge.
GitHub topics include gpu, large-large-models and cuda.
Package Insights
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100