ForgeKernel goes open source after outperforming DeepSeek’s FlashMLA kernel on B200
AI零帧起手写算子，反超DeepSeek人类手写巅峰：快了9.8%！
What happened
QbitAI reports that ForgeKernel, an autonomous kernel-generation system from ModelBest, was open-sourced after a 22.5-hour livestream optimizing DeepSeek-V4.1’s FlashMLA Prefill kernel on an NVIDIA B200. Given mathematical definitions and hardware constraints without DeepSeek’s implementation, it completed 42 iterations and reached 472 microseconds versus FlashMLA’s 518 microseconds, a reported 9.8% speedup. The system separates architecture planning from implementation, retains experimentally validated hardware knowledge, and iteratively competes against its own best versions.
Why it matters
Separating architecture planning from implementation and retaining measured hardware knowledge offers a transferable approach to kernel optimization across platforms with different architectures and profiling tools.
Read next
More changes in today’s briefingMistral releases improved Mistral Large 4 open weights for coding and cybersecurityKeep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-10-30