{"slug":"flashmla","name":"FlashMLA","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"yes","officialUrl":"https://github.com/deepseek-ai/FlashMLA","repo":"https://github.com/deepseek-ai/FlashMLA","latestVersion":"","latestRelease":"","stars":13148,"starsAsOf":"2026-10-22","description":"FlashMLA: Efficient Multi-head Latent Attention Kernels","descriptionZh":"DeepSeek MLA 解码内核","callMethods":["SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":[],"language":"C++","lastPush":"2026-10-15","formerly":null,"packages":[],"recentVersions":[],"alternatives":["ollama","llama-cpp","vllm","cherry-studio","localai","exo","sglang","mlx"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"开源大库收录：DeepSeek MLA 解码内核","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/flashmla.json","pages":{"en":"https://aimap.page/en/software/flashmla/","zh-hans":"https://aimap.page/zh-hans/software/flashmla/"}}