[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-sakana-nvidia-twell-20pct-sparse-batch-gemm":3,"topics-all":36,"news-related-748a4486-34e7-4215-b515-7eb56b3258c5":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"748a4486-34e7-4215-b515-7eb56b3258c5","TwELL：Sakana AI与NVIDIA联合提出稀疏LLM推理加速20%，解决GPU批处理落地难题","现代大语言模型的前馈层占据了超过三分之二的模型参数和80%以上的总FLOPs，而推理时对任意给定token，超过99%的隐藏激活值可以为零。这种天然的激活稀疏性本应带来巨大效率提升，但GPU高度优化的稠密矩阵运算（Tensor Core）无法有效利用——稀疏操作的额外转换开销往往抵消了跳过零值带来的收益。\n\n之前的稀疏LLM内核（TurboSparse、ProSparse、Q-Sparse等）只瞄准了单token GEMV场景，但实际训练和高吞吐推理处理的都是大批量token的GEMM运算，稠密基准在现代GPU上通过大tile和Tensor Core实现数量级更高的FLOP\u002Fs，稀疏开销反而更大。\n\nSakana AI与NVIDIA联合提出TwELL（Tile-wise ELL）稀疏格式，核心创新在于：将列划分为与matmul kernel tile大小匹配的水平块，在块内局部打包非零值——而非传统ELL格式的按行全局打包。TwELL可在现有gate projection kernel的epilogue中直接构造，无需额外kernel启动、额外全局内存读写或同步开销。推理阶段，融合kernel联合执行up projection和down projection，中间隐藏状态从不写回全局内存，每一次前向传播都减少了DRAM流量。\n\n使用TwELL内核的稀疏LLM在H100 GPU上实现了推理前向传播加速20.5%、训练加速21.9%，同时降低能耗和内存占用。实现方式极为简单：只需将SiLU激活函数替换为ReLU，并在隐藏前馈激活上添加L1正则项（系数2×10⁻⁵）。在1.5B模型上，ReLU精度略低于SiLU（46.4% vs 47.1%），但被效率收益完全覆盖。稀疏性在大约1,000步（~1B tokens）内快速稳定。\n\nTwELL的价值在于真正解决了稀疏性从研究走向生产的难题——从单token GEMV走向batch GEMM。对整个行业而言，这是一个方向性验证：超过99%的激活为零，TwELL首次让它在批处理场景中兑现为真实的加速。20%以上的推理加速意味着相同硬件可服务更多用户，或用更少GPU完成相同吞吐量。论文已发表于ICML 2026，代码已开源。","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F05\u002F11\u002Fsakana-ai-and-nvidia-introduce-twell-with-cuda-kernels-for-20-5-inference-and-21-9-training-speedup-in-llms\u002F","8382d60c-c2c4-49c5-9638-8518b803f88f",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7ac06d8e-b074-4147-abfc-ffaa4c6b8744","ai-efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"6130c28a-11f0-4af3-9311-faf38025e527","en","TwELL: 20% sparse speedup that survives GPU batching","TwELL, a joint paper from Sakana AI and NVIDIA, presents 20.5% inference and 21.9% training speedup on LLMs through custom CUDA kernels. The key contribution is making sparse models work efficiently in batched GPU serving — a problem that has hindered production deployment of sparse LLMs.","sakana-nvidia-twell-20pct-sparse-batch-gemm","2026-05-30T08:20:00Z","2026-05-30T16:15:55.955068Z","2026-08-19T02:08:40.142862Z",true,"agent",200,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"2fa66657-afbb-4f03-849a-f420f42cf2ab","Prompt Caching：LLM推理成本削减90%的隐藏利器","prompt-caching-90pct-token-cost","2026-05-26T01:10:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"73f4d31e-745a-4bba-8a0f-38e7564966de","Sakana AI 提出 99% 稀疏性Transformer：在前馈层动刀革新LLM效率","sakana-99pct-sparse-ffn-transformer","2026-05-16T19:04:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"137ce22e-389d-47fb-8219-42ca53d6e916","Qwen 3.6 27B 重磅更新：MTP 技术让本地推理提速 2.5 倍","qwen-3-6-27b-mtp-local-2-5x","2026-05-16T01:01:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"4556940e-6456-43ce-b9b4-a0a7fa7a5865","MIT 新方法：自适应草稿模型将推理 LLM 训练速度提升 2-3 倍","mit-adaptive-draft-speculative-train-2-3x","2026-05-15T02:05:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"e4fd45e9-e0fd-4839-973e-909a442ce5ff","DeepSeek V3.2稀疏注意力：如何将长上下文推理成本砍半","deepseek-v3-2-dsa-sparse-attention-50pct-cost-cut","2026-05-01T10:15:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"810251ee-b8bf-4fef-a9d8-e167c22ae4c5","BoostLoRA：梯度增强让低秩适配器「自我进化」，小参数也能有大表达","boostlora-gradient-boosting-lora-residual","2026-05-01T05:10:00+00:00"]