llama.cpp 主线合并 DeepSeek-V4.1-Flash 支持（PR 31086）
PR 31086 凌晨合入 master：新增 deepseek41 架构，39 个文件约 2800 行，自带转换脚本，--dspark 把权重里的 MTP 块打包成 DFlash 草稿模型，含视觉塔；尚无 tag 版，需从 master 编译。
DeepSeek-V4.1-Flash just landed in mainline llama.cpp. PR 31086 merged into master at 01:43 this morning: a new deepseek41 architecture, about 2,800 lines across 39 files, and its own conversion script. The part I care about: the convert step packs the checkpoint's own MTP blocks into a DFlash draft with --dspark. Mainline gets the model and a drafter without a second download. Vision tower is in there too. No tagged release yet (v0.7.0 is 15 October), so it's build-from-master. Still, not as fast as @PeasantSmith Project Maya (most like 75% of Strata's DS support came from his fork btw...) https://github.com/ggml-org/llama.cpp/pull/31086