[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-sakana-99pct-sparse-ffn-transformer":3,"topics-all":36,"news-related-73f4d31e-745a-4bba-8a0f-38e7564966de":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},"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","当业界还在讨论量化与MoE两条路线时，Sakana AI与NVIDIA合作开辟了第三条路——非结构化稀疏。该团队最新论文证明，通过在前馈层（FFN）引入稀疏性，可以在几乎不损失性能的前提下，将LLM的吞吐量、能耗和内存占用压缩到原来的几分之一。\n\n大语言模型的参数主要集中在前馈网络，它占据了70%以上的参数和执行FLOPs。团队通过简单的L1正则化，在多个主流模型中诱导出超过99%的稀疏度——即超过99%的FFN参数在大多数token推理时可以跳过。\n\n然而非结构化稀疏很难被现代GPU的密集计算管线高效执行。针对这一问题，团队设计了一套新的稀疏打包格式和配套CUDA内核，能无缝接入现代GPU的优化执行管线，让稀疏计算在训练和推理阶段都保持高效率。\n\n论文最重要的结论是：稀疏性带来的收益随模型规模增长而增加。在70B+级别的大模型上，单位算力能处理的token数量会大幅上升，内存带宽压力显著缓解。这与MoE的特性相似——更大的模型从稀疏性中获益更多。\n\n该工作已于2026年5月8日更新v2版本，代码已在GitHub开源。在LLM推理成本持续攀升的背景下，稀疏化有望成为下一代部署优化的重要选项。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.23198","7437aeb9-930c-4866-a2e9-48003c1a792b",[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},"4d03e272-fb1c-4aa0-af50-184a3bdc6859","en","Sakana AI: 99% sparse Transformers via feed-forward surgery","While the industry is still discussing the two routes of quantization and MoE, Sakana AI and NVIDIA have blazed a third trail — unstructured sparsity. The team's latest paper proves that by introducing sparsity in the feed-forward layers (FFN), LLM throughput, energy consumption, and memory footprint can be compressed to a fraction of the original with almost no performance loss.\n\nThe LLM's parameters are concentrated in the feed-forward network, accounting for over 70% of parameters and FLOPs. The team, through simple L1 regularization, induced over 99% sparsity in multiple mainstream models — meaning over 99% of FFN parameters can be skipped for most token inferences.\n\nHowever, unstructured sparsity is hard to execute efficiently on modern GPUs' dense compute pipelines. To address this, the team designed a new sparse-packing format and accompanying CUDA kernels that seamlessly integrate with modern GPU optimized execution pipelines, keeping sparse compute efficient in both training and inference stages.\n\nThe paper's most important conclusion: the gains from sparsity increase with model scale. On 70B+ level large models, the number of tokens processable per unit compute increases substantially, and memory-bandwidth pressure eases significantly. This is similar to MoE's characteristic — larger models benefit more from sparsity.\n\nThe work was updated to v2 on May 8, 2026, with code open-sourced on GitHub. Against the backdrop of continuously rising LLM inference costs, sparsification is expected to become an important option for the next generation of deployment optimization.","sakana-99pct-sparse-ffn-transformer","2026-05-16T19:04:00Z","2026-05-16T19:06:43.859627Z","2026-08-19T02:08:40.142862Z",true,"agent",209,[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},"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","sakana-nvidia-twell-20pct-sparse-batch-gemm","2026-05-30T08:20:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"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":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"]