[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-partinfer-neuron-level-edge-llm":3,"topics-all":36,"news-related-47f025dd-69eb-4fcb-b4cc-1c6d4e03ca66":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},"47f025dd-69eb-4fcb-b4cc-1c6d4e03ca66","PartInfer：神经元级优化突破边缘设备LLM推理瓶颈","大语言模型在边缘设备上的高效部署长期受制于巨大的显存和算力需求。传统模型压缩方法依赖粗粒度剪枝或量化，往往牺牲精度或需要重新训练。PartInfer提出了神经元级优化框架，通过离线分析识别任务特定神经元和通用神经元，实现两大核心优化：部分加载（Partial Loading）仅加载最重要神经元子集，大幅降低显存占用；部分计算（Partial Computation）在运行时动态计算最相关神经元。实验表明，PartInfer在多个NLP任务上实现显著的显存和算力削减，同时保持任务性能，为边缘设备上的LLM部署提供了可行路径。\n\n该研究来自OpenReview，专注于解决LLM在资源受限边缘设备上的高效推理问题。相比现有方法，PartInfer的创新在于神经元级细粒度优化，能够识别并复用任务相关的激活模式，在不损失精度的前提下实现深度压缩。随着端侧AI需求的增长，这类技术有望成为移动端和嵌入式设备上部署大模型的关键使能技术。","https:\u002F\u002Fopenreview.net\u002Fforum?id=3sbM94O8Ts","ec0a79b7-694c-4caf-8071-91315d69c706",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"fca9258a-9430-455a-b95d-b9fae5e373a8","ai-inference",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"2d9c2fb0-2be5-4ad1-aedb-e9747addf355","compression",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"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},"90fe3788-6776-4788-bd11-c91df574ea09","en","PartInfer: neuron-level optimization breaks edge inference limits","PartInfer, published at OpenReview, presents neuron-level optimization for edge-device LLM inference. Instead of treating the model as a uniform graph, PartInfer identifies \"important\" and \"less important\" neurons via gradient analysis, and applies different optimization (quantization, pruning, KV-cache strategy) to each. The result is significantly better quality-efficiency trade-off on edge devices.","partinfer-neuron-level-edge-llm","2026-06-03T04:00:00Z","2026-06-03T04:23:01.836817Z","2026-08-19T02:08:40.142862Z",true,"agent",161,[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},"bc642ebf-9b1c-41cf-98d1-dd55393fd429","HeadWiseKV:无训练KV cache压缩让混合LLM长上下文从114K推到161K","headwisekv-training-free-kv-cache-compression","2026-09-03T03:44:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"e91b3add-4f1d-48d3-ab7a-bd2c6e8c1765","QuIP 崩、OPTQ 降级:Kashin-DCT 在 4-bit 量化压力测试里活了下来","kashin-dct-2bit-llm-quantization","2026-09-12T15:10:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"c83af54b-79ed-445c-9482-07d98c26c36b","BeaconKV:长推理会回头看,只压最近窗口的 KV 缓存注定丢东西","beaconkv-beacon-query-kv-cache-compression","2026-09-09T11:25:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"bce9fc16-d31a-49be-b17b-f144619a58e2","LatentPress:上下文压成软令牌直读，7.7 倍压缩反超原文，训练仅动 0.1% 参数","latentpress-soft-token-context-compression","2026-09-05T19:06:09+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"d31bc388-b6c7-41a5-a6e9-6f00657c7616","加GPU还是压KV缓存？arXiv论文：压缩省钱1.2到2倍，但36B是道坎","tensor-parallelism-vs-kv-compression-cost","2026-08-30T17:10:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"f65e204c-0115-4b50-9113-2c3bb2ff6637","ReCache:给 Agent 的工具记忆装上独立缓存,KV 内存砍 92%、首 token 提速 3.655 倍","recache-agent-kv-cache-reuse","2026-08-24T15:30:00+00:00"]