tokenspeed-mla has 1.5M monthly downloads and 2K GitHub stars. Version 0.1.8 supports Python 3.10+, first published in 2026.
It is actively maintained under a permissive license, last released in Jun 2026.
It is built on top of apache-tvm-ffi, nvidia-cutlass-dsl and tokenspeed-triton. It is used by 3 tracked packages, including sglang, vllm and lsglang.
GitHub topics include deepseek, gpt-oss and kimi.
Package Insights
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100Weekly Downloads
GitHub Stars
Downloads by OS
Python Versions
Top Countries
Dependencies
- apache-tvm-ffi <=0.1.11,>=0.1.5
- nvidia-cutlass-dsl
- tokenspeed-triton >=3.7.10.post20260531
- torch