Open-Source PTX KDA Kernel Released for Blackwell

INT21-AI open-sourced the PTX KDA kernel for Kimi, achieving up to 1.59x speedup over FlashKDA on NVIDIA Blackwell GPUs.

2026-07-28 ~ 2026-07-28 · 2 related posts

• Open-Sourced PTX KDA Kernel Delivers 1.59x Speedup Over FlashKDA — JFPuget · 2026-07-28
• Open-source KDA-B200 kernel claims up to 1.59× speedup on NVIDIA Blackwell GPUs — xennygrimmato_ · 2026-07-28