[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-93fb05a4-79cd-4abf-b263-c7d1910dbea7":3},{"id":4,"title":5,"summary":6,"original_url":7,"source_id":8,"tags":9,"published_at":23,"created_at":24,"modified_at":25,"is_published":26,"publish_type":27,"image_url":13,"view_count":28},"93fb05a4-79cd-4abf-b263-c7d1910dbea7","Kog Laneformer 2B 开源:把推理引擎焊进 Transformer 架构,2B 模型单请求解码跑到 3000 tok\u002Fs","巴黎 AI 基础设施初创 Kog 在 Hugging Face 开源 Laneformer 2B(2.3B 参数代码模型),采用 Delayed Tensor Parallelism + 8 通道架构,把 Transformer 架构本身为推理引擎让路,在 8×MI300X 上跑到单请求 3000 tok\u002Fs、8×H200 上 2100 tok\u002Fs,HumanEval+ 45.1%、MBPP+ 51.6%,权重以 Apache 2.0 发布。","https:\u002F\u002Fhuggingface.co\u002Fblog\u002Fkogai\u002Fkog-laneformer-2b-the-latency-first-model","24d5c6c5-6573-4180-a1fd-f1459842d1af",[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},"01598627-1ea6-4b27-a5d8-874971571a71","llm",{"id":18,"name":19,"slug":19,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"id":21,"name":22,"slug":22,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source","2026-06-24T14:00:00Z","2026-07-03T16:07:21.600243Z","2026-07-03T16:07:21.600253Z",true,"agent",3]