[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"site-home-live-entry-setting":3,"site-header-contests":8,"news-detail-news-8":49,"site-header-camps":89},{"enabled":4,"title":5,"statusText":5,"buttonText":5,"campSlug":5,"stage":6,"classroomId":7,"hasClassroom":4},false,"",0,null,{"total":9,"list":10,"pageNum":44,"pageSize":45,"size":9,"startRow":44,"endRow":9,"pages":44,"prePage":6,"nextPage":6,"isFirstPage":46,"isLastPage":46,"hasPreviousPage":4,"hasNextPage":4,"navigatePages":47,"navigatepageNums":48,"navigateFirstPage":44,"navigateLastPage":44},3,[11,25,35],{"slug":12,"title":13,"logo":7,"liveUrl":14,"prize":15,"sponsor":16,"description":17,"organizer":18,"startTime":19,"endTime":20,"registrationDeadline":21,"status":22,"dashboardVisibility":23,"createdAt":24},"spring2026","2026春季启元人工智能大赛","https:\u002F\u002Fwww.bilibili.com\u002Fblackboard\u002Flive\u002Flive-activity-player.html?cid=1822703816&quality=0","200,000","麒麟软件有限公司","“2026春季启元人工智能大赛”是由启元实验室主办的面向全国人工智能领域开发者、科研人员及高校学生的权威赛事。大赛旨在促进与培养具备工程实践能力和创新能力的优秀人工智能领域开发者、推广国产软硬件技术与生态、助力国家人工智能产业高质量发展。\n各参赛选手需在规定的比赛周期内，依据赛事规则选定赛题并完成相应挑战，优胜者将共同角逐总额20万元的赛事奖金池，并且还将有机会获得实习和知名企业优质岗位内推资格。","启元实验室","2026-04-19 16:00:00","2026-07-13 16:00:00","2026-06-16 16:00:00","ongoing","private","2026-04-16 08:00:00",{"slug":26,"title":27,"logo":7,"liveUrl":14,"prize":28,"sponsor":7,"description":29,"organizer":18,"startTime":30,"endTime":31,"registrationDeadline":32,"status":33,"dashboardVisibility":23,"createdAt":34},"autumn2025","2025秋季启元人工智能大赛","150,000","“2025秋季启元人工智能大赛”是由启元实验室主办的面向全国人工智能领域开发者、科研人员及高校学生的权威赛事。大赛旨在促进与培养具备工程实践能力和创新能力的优秀人工智能领域开发者、推广国产软硬件技术与生态、助力国家人工智能产业高质量发展。","2025-11-08 08:00:00","2026-01-13 08:00:00","2025-12-30 08:00:00","ended","2025-11-03 08:00:00",{"slug":36,"title":37,"logo":7,"liveUrl":14,"prize":38,"sponsor":7,"description":39,"organizer":18,"startTime":40,"endTime":41,"registrationDeadline":42,"status":33,"dashboardVisibility":23,"createdAt":43},"summer2025","启元人工智能大赛(系统方向)","80,000","启元人工智能大赛由启元实验室主办，其中系统赛道基于启元实验室九源软件栈的相关开源项目，通过拉动开源社区力量，一方面促进国产智能计算生态的发展，另一方面也为人工智能系统方向的学生及从业者提供一个实践平台。","2025-07-08 08:00:00","2025-08-25 08:00:00","2025-07-22 08:00:00","2025-06-22 08:00:00",1,5,true,8,[44],{"newsDetail":50,"processedData":72},{"publishTime":51,"img":52,"keywords":53,"treeType":44,"description":54,"showStatus":44,"updateTime":55,"type":44,"title":56,"content":57,"nextArticle":58,"createTime":55,"sortOrder":63,"canonicalPath":64,"id":65,"contentType":66,"prevArticle":67},"2025-11-22 08:00:00","https:\u002F\u002Foss.infinitensor.com\u002Fprod\u002Fimages\u002Fportal_news\u002Fnews_01.jpg?Expires=1792752919&OSSAccessKeyId=LTAI5t9R6uzvTa69CT92cFvV&Signature=dy0JDndyVjyTcQhT19v43miqUt8%3D","TileLang,九齿,编译原型,语言设计,技术演进","文章梳理从 TileLang 到九齿编译原型的演进路径，重点说明语言抽象设计、编译实现思路与工程化探索方向。","2026-10-22 20:38:11","从 TileLang 到九源统一领域编程语言（九齿）的编译原型","![](https:\u002F\u002Ffastly.jsdelivr.net\u002Fgh\u002Fbucketio\u002Fimg12@main\u002F2025\u002F11\u002F22\u002F1763786497818-1e0bf4ed-728b-4176-85bc-39788649674e.png?width=500px&margin=auto)\r\n\r\n\r\n>九源统一领域编程语言（九齿）现已实现对 TileLang 的支持！\r\n\r\n我们已完成原型编译器，实现了将以 TileLang 编写的矩阵乘法等关键计算内核高效编译至九齿的中间表示（IR），并进一步转化为优化的 Triton 代码，进而使其能够无缝运行于包括 NVIDIA GPU 和多款国产智能芯片在内的广泛硬件平台。此举标志着九源在构建统一智能计算软件栈上迈出了关键一步，大幅降低了国产平台基础编译设施的研发负担。\r\n\r\n## 性能评估\r\n\r\n![](https:\u002F\u002Ffastly.jsdelivr.net\u002Fgh\u002Fbucketio\u002Fimg17@main\u002F2025\u002F11\u002F22\u002F1763783133396-2fd0f8ca-7b4b-466b-9f16-3c728cd1c565.png?width=500px&margin=auto)\r\n\r\n图1 在 RTX 4060 Laptop GPU 上的性能对比\r\n\r\n## 九源领域编程语言-九齿\r\n九齿是一门基于 Triton 的领域特定语言（DSL），旨在进一步简化高性能计算内核的开发。它通过引入面向张量的元编程（tensor-oriented metaprogramming），抽象掉了指针算术运算和内存访问等底层细节，能够降低并行编程的门槛。九齿能够让开发者使用少量简洁的代码实现较高性能的计算内核，并且可以提高代码的可读性和可维护性。\r\n\r\n\r\n## TileLang\r\nTileLang 是一门面向高性能深度学习算子的领域专用语言（DSL）。它致力于在编程语言层提供结构化表达，用以统一建模算子、调度策略与硬件映射。其核心设计理念是将复杂的硬件调度与开发者的算法逻辑解耦，将调度空间（包括线程绑定、内存布局等）与数据流解耦，并封装为一组可自定义的注解和原语。这使得开发者能更专注于计算内核的数据流本身，而将多数优化工作交由编译器自动完成，显著提升了AI算子的开发效率和可维护性。TileLang 采用 Python 式简洁语法，并提供了分层接口以适应从初学者到硬件专家的不同层次开发者。\r\n\r\n## Triton\r\nTriton 是一种专为简化高性能深度学习计算内核开发而设计的编程语言和编译器。它允许开发人员使用类似于 Python 的语法编写可编译为高效 GPU 代码的程序，这一特性大大降低了 GPU 代码的开发难度。相较于传统的开发方式，Triton 使得编写与专业库性能相当的高效内核成为可能，且代码更为简洁。\r\n\r\n\r\n### 📚 知识充电站\r\n如果你希望持续获取 AI 系统优化、大模型、CUDA 编程等方向的前沿解析与技术干货，欢迎关注我们的公众号 **「InfiniTensor」**。在这里，我们不仅分享知识，更致力于构建一个共同成长的学习社区。",{"publishTime":59,"createTime":55,"canonicalPath":60,"id":61,"title":62},"2025-11-21 08:00:00","\u002Fnews\u002Fnews-3","news-3","本周日！别错过！2025秋季启元人工智能大赛启动会直播在即！",66,"\u002Fnews\u002Fnews-8","news-8","markdown",{"publishTime":68,"createTime":55,"canonicalPath":69,"id":70,"title":71},"2025-11-27 08:00:00","\u002Fnews\u002Fnews-7","news-7","CCF 中国软件大会学术论坛——「高性能统一智能计算架构的系统软件」邀您参加！",{"htmlContent":73,"headings":74},"\u003Cp>\u003Cimg src=\"https:\u002F\u002Ffastly.jsdelivr.net\u002Fgh\u002Fbucketio\u002Fimg12@main\u002F2025\u002F11\u002F22\u002F1763786497818-1e0bf4ed-728b-4176-85bc-39788649674e.png?width=500px&margin=auto\" alt=\"\" style=\"width:500px;margin:auto\">\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>九源统一领域编程语言（九齿）现已实现对 TileLang 的支持！\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>我们已完成原型编译器，实现了将以 TileLang 编写的矩阵乘法等关键计算内核高效编译至九齿的中间表示（IR），并进一步转化为优化的 Triton 代码，进而使其能够无缝运行于包括 NVIDIA GPU 和多款国产智能芯片在内的广泛硬件平台。此举标志着九源在构建统一智能计算软件栈上迈出了关键一步，大幅降低了国产平台基础编译设施的研发负担。\u003C\u002Fp>\n\u003Ch2 id=\"性能评估\">\u003Ca class=\"anchor\" href=\"#性能评估\" aria-label=\"跳转到标题：性能评估\">\u003Cspan class=\"octicon octicon-link\">\u003C\u002Fspan>\u003C\u002Fa>性能评估\u003C\u002Fh2>\u003Cp>\u003Cimg src=\"https:\u002F\u002Ffastly.jsdelivr.net\u002Fgh\u002Fbucketio\u002Fimg17@main\u002F2025\u002F11\u002F22\u002F1763783133396-2fd0f8ca-7b4b-466b-9f16-3c728cd1c565.png?width=500px&margin=auto\" alt=\"\" style=\"width:500px;margin:auto\">\u003C\u002Fp>\n\u003Cp>图1 在 RTX 4060 Laptop GPU 上的性能对比\u003C\u002Fp>\n\u003Ch2 id=\"九源领域编程语言-九齿\">\u003Ca class=\"anchor\" href=\"#九源领域编程语言-九齿\" aria-label=\"跳转到标题：九源领域编程语言-九齿\">\u003Cspan class=\"octicon octicon-link\">\u003C\u002Fspan>\u003C\u002Fa>九源领域编程语言-九齿\u003C\u002Fh2>\u003Cp>九齿是一门基于 Triton 的领域特定语言（DSL），旨在进一步简化高性能计算内核的开发。它通过引入面向张量的元编程（tensor-oriented metaprogramming），抽象掉了指针算术运算和内存访问等底层细节，能够降低并行编程的门槛。九齿能够让开发者使用少量简洁的代码实现较高性能的计算内核，并且可以提高代码的可读性和可维护性。\u003C\u002Fp>\n\u003Ch2 id=\"tilelang\">\u003Ca class=\"anchor\" href=\"#tilelang\" aria-label=\"跳转到标题：TileLang\">\u003Cspan class=\"octicon octicon-link\">\u003C\u002Fspan>\u003C\u002Fa>TileLang\u003C\u002Fh2>\u003Cp>TileLang 是一门面向高性能深度学习算子的领域专用语言（DSL）。它致力于在编程语言层提供结构化表达，用以统一建模算子、调度策略与硬件映射。其核心设计理念是将复杂的硬件调度与开发者的算法逻辑解耦，将调度空间（包括线程绑定、内存布局等）与数据流解耦，并封装为一组可自定义的注解和原语。这使得开发者能更专注于计算内核的数据流本身，而将多数优化工作交由编译器自动完成，显著提升了AI算子的开发效率和可维护性。TileLang 采用 Python 式简洁语法，并提供了分层接口以适应从初学者到硬件专家的不同层次开发者。\u003C\u002Fp>\n\u003Ch2 id=\"triton\">\u003Ca class=\"anchor\" href=\"#triton\" aria-label=\"跳转到标题：Triton\">\u003Cspan class=\"octicon octicon-link\">\u003C\u002Fspan>\u003C\u002Fa>Triton\u003C\u002Fh2>\u003Cp>Triton 是一种专为简化高性能深度学习计算内核开发而设计的编程语言和编译器。它允许开发人员使用类似于 Python 的语法编写可编译为高效 GPU 代码的程序，这一特性大大降低了 GPU 代码的开发难度。相较于传统的开发方式，Triton 使得编写与专业库性能相当的高效内核成为可能，且代码更为简洁。\u003C\u002Fp>\n\u003Ch3 id=\"知识充电站\">\u003Ca class=\"anchor\" href=\"#知识充电站\" aria-label=\"跳转到标题：📚 知识充电站\">\u003Cspan class=\"octicon octicon-link\">\u003C\u002Fspan>\u003C\u002Fa>📚 知识充电站\u003C\u002Fh3>\u003Cp>如果你希望持续获取 AI 系统优化、大模型、CUDA 编程等方向的前沿解析与技术干货，欢迎关注我们的公众号 \u003Cstrong>「InfiniTensor」\u003C\u002Fstrong>。在这里，我们不仅分享知识，更致力于构建一个共同成长的学习社区。\u003C\u002Fp>\n",[75,78,80,83,86],{"id":76,"text":76,"level":77},"性能评估",2,{"id":79,"text":79,"level":77},"九源领域编程语言-九齿",{"id":81,"text":82,"level":77},"tilelang","TileLang",{"id":84,"text":85,"level":77},"triton","Triton",{"id":87,"text":88,"level":9},"知识充电站","📚 知识充电站",{"total":45,"list":90,"pageNum":44,"pageSize":45,"size":45,"startRow":44,"endRow":45,"pages":44,"prePage":6,"nextPage":6,"isFirstPage":46,"isLastPage":46,"hasPreviousPage":4,"hasNextPage":4,"navigatePages":47,"navigatepageNums":143,"navigateFirstPage":44,"navigateLastPage":44},[91,102,113,124,134],{"id":92,"slug":93,"title":94,"logo":95,"publicLiveEmbedUrl":14,"description":96,"introduction":97,"organizer":18,"coOrganizer":5,"sponsor":16,"startTime":98,"endTime":99,"status":22,"dashboardVisibility":100,"createdAt":98,"updatedAt":101},"019eeeff-6b00-7d55-a629-efafded3e232","summer2026","2026年夏季InfiniTensor大模型与人工智能系统训练营","https:\u002F\u002Foss.infinitensor.com\u002Fprod\u002Fuploads\u002F2026-06\u002F019eef7f-7816-7828-9309-79c2c61dd568.jpg?Expires=1792752919&OSSAccessKeyId=LTAI5t9R6uzvTa69CT92cFvV&Signature=LJ0ZuxNgIJ4RyVgczKT23b4nC1U%3D","由启元实验室发起的InfiniTensor大模型与人工智能系统训练营，面向开源社区、高校及产业界伙伴开放。活动以「普及AI全栈知识技术、培养工程实践与创新型人才、推广国产软硬件技术生态」为核心目标，助力国家人工智能产业高质量发展。","...","2026-06-22 08:00:00","2026-10-19 08:00:00","public","2026-10-12 08:00:00",{"id":103,"slug":104,"title":105,"logo":106,"publicLiveEmbedUrl":7,"description":107,"introduction":97,"organizer":18,"coOrganizer":5,"sponsor":108,"startTime":109,"endTime":110,"status":33,"dashboardVisibility":23,"createdAt":111,"updatedAt":112},"019af3f3-e06a-7245-aa8d-37dc99a69c73","winter2025","2025年冬季InfiniTensor大模型与人工智能系统训练营","https:\u002F\u002Foss.infinitensor.com\u002Fprod\u002Fuploads\u002F2025-12\u002F019afc69-b7ca-7805-91fb-605429671c01.png?Expires=1792752919&OSSAccessKeyId=LTAI5t9R6uzvTa69CT92cFvV&Signature=QAVpGIqmRmM53c0O1pqgr%2F6rmnc%3D","由启元实验室发起的InfiniTensor大模型与人工智能系统训练营，面向开源社区、高校及产业界伙伴开放。活动以「普及AI全栈知识技术、培养工程实践与创新型人才、推广国产软硬件技术生态」为核心目标，助力国家人工智能产业高质量发展。 \n","新华三技术有限公司","2025-12-25 08:00:00","2026-03-27 08:00:00","2025-12-06 08:00:00","2026-10-22 20:24:30",{"id":114,"slug":36,"title":115,"logo":116,"publicLiveEmbedUrl":7,"description":117,"introduction":97,"organizer":18,"coOrganizer":5,"sponsor":118,"startTime":119,"endTime":120,"status":121,"dashboardVisibility":23,"createdAt":122,"updatedAt":123},"01980342-208c-7803-b3f3-19e1d31960ba","2025年夏季InfiniTensor大模型与人工智能系统训练营","https:\u002F\u002Foss.infinitensor.com\u002Fprod\u002Fuploads\u002F2025-07\u002F0198045e-28fe-78f0-95fe-23835ce58395.jpg?Expires=1792752919&OSSAccessKeyId=LTAI5t9R6uzvTa69CT92cFvV&Signature=Ax3dDPChIYk86aZzWXZANpD9s%2BY%3D","InfiniTensor大模型与人工智能系统训练营由启元实验室及清华大学 AI 系统方向团队发起，面向开源社区、高校和产业界，普及人工智能各方面知识和技术，培养相关人才。训练营联合开源项目开发者、学术界大牛、工业界资深工程师参与授课与项目指导。课程采用「线上直播授课 + 在线答疑 + 项目实践辅导 」的方式进行，确保每位同学都能获得充分成长。训练营全程免费，通过视频、直播课、习题和项目实践，在人工智能飞速发展的背景下，为学员提供一窥深层技术的机会。","北京积算科技有限公司","2025-07-14 08:00:00","2025-09-30 08:00:00","upcoming","2025-07-13 08:00:00","2026-10-22 20:24:58",{"id":125,"slug":126,"title":127,"logo":128,"publicLiveEmbedUrl":7,"description":129,"introduction":97,"organizer":18,"coOrganizer":5,"sponsor":5,"startTime":130,"endTime":131,"status":121,"dashboardVisibility":23,"createdAt":132,"updatedAt":133},"01980cf9-a7d8-7796-ae86-0bbe05334add","winter2024","2024年冬季InfiniTensor大模型与人工智能系统训练营","https:\u002F\u002Ftesting-cdn.infinitensor.com\u002Fuploads\u002F2025-07\u002F01981269-ce23-7624-a287-9f07dd0d85f6.jpg","InfiniTensor大模型与人工智能系统训练营由清华大学发起，面向开源社区、高校和产业界，普及人工智能各方面知识和技术，培养相关人才。训练营全程免费，通过视频、直播课、习题和项目实践，在人工智能飞速发展的背景下，为学员提供一窥深层技术的机会。报名学员请阅读“导学”课程页的训练营介绍。","2025-01-05 08:00:00","2025-03-22 08:00:00","2025-07-15 08:00:00","2026-10-22 20:24:39",{"id":135,"slug":136,"title":137,"logo":138,"publicLiveEmbedUrl":7,"description":139,"introduction":97,"organizer":18,"coOrganizer":5,"sponsor":5,"startTime":140,"endTime":141,"status":121,"dashboardVisibility":23,"createdAt":132,"updatedAt":142},"01980c20-363a-7dc3-8f5a-58a68e08dcc4","summer2024","2024年夏季InfiniTensor大模型与人工智能系统训练营","https:\u002F\u002Ftesting-cdn.infinitensor.com\u002Fuploads\u002F2025-07\u002F01981269-fbfa-788a-afcd-17fa9be74ff9.jpg","InfiniTensor大模型与人工智能系统训练营由清华大学发起，面向开源社区和高校，普及人工智能各方面知识和技术，培养相关人才。训练营全程免费，通过课程、习题和项目实践，在人工智能飞速发展的背景下，为学员提供一窥深层技术的机会。","2024-07-20 08:00:00","2024-09-29 08:00:00","2026-10-22 20:24:49",[44]]