史上最快大模型炸场！Groq一夜爆红，自研LPU速度碾压英伟达GPU_老虎社区_美港股上老虎

史上最快大模型炸场！Groq一夜爆红，自研LPU速度碾压英伟达GPU

华尔街见闻02-20

英伟达的挑战者Groq登场！抛弃GPU，自研LPU！文本生成速度比眨眼还快！推理场景速度比英伟达GPU快10倍，但价格和耗电量都仅为后者十分之一。一觉醒来，AI圈又变天了。还没消化完Sora带来的震撼，又一家硅谷初创企业带着史上最快的大模型和自研芯片LPU霸占了热搜。就在昨天，AI芯片创企Groq（不是马斯克的Gork）开放了自家产品的免费试用。相比其他AI聊天机器人，Groq闪电般的响应速度迅速...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

Kenny Gong
·02-21
三星？
回复
点赞
举报
发型很乱
·02-20
明显是小母牛放屁——吹牛B
回复
点赞
举报
神刀
·02-20
天下武功唯快不破
回复
1
举报
embcx
·02-20
对英伟达是个挑[微笑]
回复
1
举报
大内金虎零零发
·02-20
牛皮啊啊啊啊
回复
1
举报
慧_4909
·02-20
牛了老大B了！
回复
点赞
举报
司徒在广州
·02-20
说说你对这篇新闻的看法...
回复
1
举报

热议股票

7x24

全部

关于我们·老虎社区守则·老虎社区账号管理规范·老虎社区服务协议·老虎社区隐私政策

公司名称：北京至简风宜信息技术有限公司

违法和不良信息投诉：010-5681-3562（工作时间9:30-18:30）

邮箱：service@laohu8.com

营业执照：91110105MA01A4U55R

ICP备：京ICP备18016422号

网安备：京公网安备11010502036490

关注我们

{"i18n":{"language":"zh_CN"},"data":{"share":"https://www.laohu8.com/m/news/2412738401?lang=zh_CN&edition=full","thumbnail":"https://static.tigerbbs.com/35fc458972611c2f98e1cc9b3e7c3b5c","is_english":false,"pubTime":"2024-02-20 19:58","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2412738401","market":"hk","top_or_hot":-1,"title":"史上最快大模型炸场！Groq一夜爆红，自研LPU速度碾压英伟达GPU","media":"华尔街见闻","content":"<div>\n<p>英伟达的挑战者Groq登场！抛弃GPU，自研LPU！文本生成速度比眨眼还快！推理场景速度比英伟达GPU快10倍，但价格和耗电量都仅为后者十分之一。一觉醒来，AI圈又变天了。还没消化完Sora带来的震撼，又一家硅谷初创企业带着史上最快的大模型和自研芯片LPU霸占了热搜。就在昨天，AI芯片创企Groq（不是马斯克的Gork）开放了自家产品的免费试用。相比其他AI聊天机器人，Groq闪电般的响应速度迅速...</p>\n\n<a href=\"https://wallstreetcn.com/articles/3708651\">网页链接</a>\n\n</div>\n","source":"wallstreetcn_hot_news","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>史上最快大模型炸场！Groq一夜爆红，自研LPU速度碾压英伟达GPU</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n史上最快大模型炸场！Groq一夜爆红，自研LPU速度碾压英伟达GPU\n</h2>\n\n<h4 class=\"meta\">\n\n\n2024-02-20 19:58 北京时间&nbsp;&nbsp;&nbsp;<a href=https://wallstreetcn.com/articles/3708651><strong>华尔街见闻</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>英伟达的挑战者Groq登场！抛弃GPU，自研LPU！文本生成速度比眨眼还快！推理场景速度比英伟达GPU快10倍，但价格和耗电量都仅为后者十分之一。一觉醒来，AI圈又变天了。还没消化完Sora带来的震撼，又一家硅谷初创企业带着史上最快的大模型和自研芯片LPU霸占了热搜。就在昨天，AI芯片创企Groq（不是马斯克的Gork）开放了自家产品的免费试用。相比其他AI聊天机器人，Groq闪电般的响应速度迅速...</p>\n\n<a href=\"https://wallstreetcn.com/articles/3708651\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"IE00BKDWB100.SGD","symbol_name":"PINEBRIDGE US LARGE CAP RESEARCH ENHANCED \"A5H\" (SGDHDG) ACC","start_time":0,"source_url":"https://wallstreetcn.com/articles/3708651","article_id":"2412738401","we_media_id":null,"thumbnails":["https://static.tigerbbs.com/35fc458972611c2f98e1cc9b3e7c3b5c"],"rights":{"source":"wallstreetcn_hot_news","url":"https://wallstreetcn.com/articles/3708651","rn_cache_url":null,"directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2412738401","pubTimestamp":1708430285,"sourceInfo":{"source_id":"wallstreetcn_hot_news","name":"华尔街见闻"},"weMediaInfo":null,"summary":"英伟达的挑战者Groq登场！抛弃GPU，自研LPU！文本生成速度比眨眼还快！推理场景速度比英伟达GPU快10倍，但价格和耗电量都仅为后者十分之一。","collect":0,"end_time":0,"defaultTopTitle":"wallstreetcn.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"IE00BKDWB100.SGD":"PINEBRIDGE US LARGE CAP RESEARCH ENHANCED \"A5H\" (SGDHDG) ACC","LU0820561909.HKD":"ALLIANZ INCOME AND GROWTH \"AM\" (HKD) INC","BK4533":"AQR资本管理(全球第二大对冲基金)","LU0109392836.USD":"富兰克林科技股A","BK4567":"ESG概念","BK4534":"瑞士信贷持仓","LU0061474960.USD":"天利环球焦点基金AU Acc","LU0353189763.USD":"ALLSPRING  US ALL CAP GROWTH FUND \"I\" (USD) ACC","IE0004445015.USD":"JANUS HENDERSON BALANCED \"A2\" (USD) ACC","IE00BJJMRY28.SGD":"Janus Henderson Balanced A Inc SGD","BK4532":"文艺复兴科技持仓","BK4554":"元宇宙及AR概念","LU0466842654.USD":"HSBC ISLAMIC GLOBAL EQUITY INDEX \"A\" (USD) ACC","LU0097036916.USD":"贝莱德美国增长A2 USD","LU0689472784.USD":"安联收益及增长基金Cl AM AT Acc","BK4141":"半导体产品","LU0198837287.USD":"UBS (LUX) EQUITY SICAV - USA GROWTH \"P\" (USD) ACC","IE00BD6J9T35.USD":"NEUBERGER BERMAN NEXT GENERATION MOBILITY \"A\" (USD) ACC","IE00B1BXHZ80.USD":"Legg Mason ClearBridge - US Appreciation A Acc USD","LU0316494557.USD":"FRANKLIN GLOBAL FUNDAMENTAL STRATEGIES \"A\" ACC","LU0444971666.USD":"天利全球科技基金","LU0061475181.USD":"THREADNEEDLE (LUX) AMERICAN \"AU\" (USD) ACC","IE00BFSS8Q28.SGD":"Janus Henderson Balanced A Inc SGD-H","BK4548":"巴美列捷福持仓","IE0034235188.USD":"PINEBRIDGE GLOBAL FOCUS EQUITY \"A\" (USD) ACC","LU0820561818.USD":"安联收益及增长平衡基金Cl AM DIS","LU0708995401.HKD":"FRANKLIN U.S. OPPORTUNITIES \"A\" (HKD) ACC","BK4549":"软银资本持仓","LU0127658192.USD":"EASTSPRING INVESTMENTS GLOBAL TECHNOLOGY \"A\" (USD) ACC","LU0256863811.USD":"ALLIANZ US EQUITY \"A\" INC","IE0009356076.USD":"JANUS HENDERSON GLOBAL TECHNOLOGY AND INNOVATION \"A2\" (USD) ACC","IE00B7KXQ091.USD":"Janus Henderson Balanced A Inc USD","LU0348723411.USD":"ALLIANZ GLOBAL HI-TECH GROWTH \"A\" (USD) INC","BK4551":"寇图资本持仓","LU0109391861.USD":"富兰克林美国机遇基金A Acc","IE0004445239.USD":"JANUS HENDERSON US FORTY \"A2\" (USD) ACC","IE00B19Z9505.USD":"美盛-美国大盘成长股A Acc","IE00BJJMRX11.SGD":"Janus Henderson Balanced A Acc SGD","LU0642271901.SGD":"Janus Henderson Horizon Global Technology Leaders A2 SGD-H","BK4550":"红杉资本持仓","LU0053666078.USD":"摩根大通基金-美国股票A（离岸）美元","LU0079474960.USD":"联博美国增长基金A","BK4543":"AI","LU0082616367.USD":"摩根大通美国科技A（dist）","GB00BDT5M118.USD":"天利环球扩展Alpha基金A Acc","LU0056508442.USD":"贝莱德世界科技基金A2","IE00B1XK9C88.USD":"PINEBRIDGE US LARGE CAP RESEARCH ENHANCED \"A\" (USD) ACC","LU0640476718.USD":"THREADNEEDLE (LUX) US CONTRARIAN CORE EQ \"AU\" (USD) ACC","NVDA":"英伟达","LU0353189680.USD":"富国美国全盘成长基金Cl A Acc"},"translate_title":"The fastest big model explosion field in history! Groq exploded overnight, and self-developed LPU speed crushed NVIDIA GPU","themeId":"","isJumpTheme":false,"ttsUrl":"https://static.tigerbbs.com/9f15aa033ce3489e342e0c88d093ac8f","symbols_score_info":{"NVDA":1},"content_text":"英伟达的挑战者Groq登场！抛弃GPU，自研LPU！文本生成速度比眨眼还快！推理场景速度比英伟达GPU快10倍，但价格和耗电量都仅为后者十分之一。一觉醒来，AI圈又变天了。还没消化完Sora带来的震撼，又一家硅谷初创企业带着史上最快的大模型和自研芯片LPU霸占了热搜。就在昨天，AI芯片创企Groq（不是马斯克的Gork）开放了自家产品的免费试用。相比其他AI聊天机器人，Groq闪电般的响应速度迅速引爆互联网讨论。经过网友测试，Groq每秒生成速度接近500 tok/s，碾压GPT-4的40 tok/s。有网友震惊地说：它回复的速度比我眨眼还快。不过，需要强调的是，Groq并没有研发新模型，它只是一个模型启动器，主页上运行的是开源模型Mixtral 8x7B-32k和Llama 270B-4k。冠绝大模型圈子的响应速度，来自驱动模型的硬件——Groq并未使用英伟达的GPU，而是自研了新型AI芯片——LPU（Language Processing Units）。每秒500 tokens，写论文比你眨眼还快LPU最突出的特点就是快。根据2024年一月的测试结果，由Groq LPU驱动Meta Llama 2模型，推理性能遥遥领先，是顶级云计算供应商的18倍。图片来源：GIT HUB华尔街见闻此前文章提及，Groq LPU搭配Meta Llama 2 70B能在7分钟内就能生成与莎士比亚《哈姆雷特》相同数量的单词，比普通人的打字速度快75倍。如下图所示，有推特网友问了一个和营销有关的专业问题，Groq在四秒钟之内就输出了上千词的长篇大论。还有网友测试同时用Gemini、GPT-4和Groq完成一个代码调试问题。结果，Groq的输出速度比Gemini快10倍，比GPT-4快18倍。Groq在速度上对其他AI模型的降维打击，让网友直呼，“AI推理界的美国队长来了”。LPU，英伟达GPU的挑战者？再强调一遍，Groq没有开发新的模型，它只是用了不一样的芯片。根据Groq官网的介绍，LPU是一种专为AI推理所设计的芯片。驱动包括GPT等主流大模型的GPU，是一种为图形渲染而设计的并行处理器，有数百个内核，而LPU架构则与GPU使用的SIMD（单指令，多数据）不同，这种设计可以让芯片更有效地利用每个时钟周期，确保一致的延迟和吞吐量，也降低了复杂调度硬件的需求：Groq的LPU推理引擎不是普通的处理单元；它是一个端到端系统，专为需要大量计算和连续处理的应用（如LLM）提供最快的推理而设计。通过消除外部内存瓶颈，LPU推理引擎的性能比传统GPU高出几个数量级。简单来说，对用户而言，最直观的体验就是“快”。使用过GPT的读者一定知道，痛苦地等待大模型一个一个地吐出字符是一种怎样痛苦的体验，而LPU驱动下的大模型，基本可以做到实时响应。比如下图，华尔街见闻向Groq询问LPU和GPU的区别，Groq生成这个回答用时不到3秒，完全不会像GPT、Gemini那样出现显著的延迟。如果以英文提问，生成速度还会更快。Groq官方的介绍还显示，创新的芯片架构可以把多个张量流处理器（Tensor Streaming Processor，简称TSP）连接在一起，而不会出现GPU集群中的传统瓶颈，因此具有极高的可扩展性，简化了大规模AI模型的硬件要求。能效也是LPU的另一个亮点。通过减少管理多个线程的开销和避免内核的利用率不足，LPU每瓦特可以提供更多的算力。Groq创始人兼首席执行官Jonathan Ross在采访中，时时不忘给英伟达上眼药。他此前对媒体表示，在大模型推理场景，Groq LPU芯片的速度比英伟达GPU快10倍，但价格和耗电量都仅为后者的十分之一。实时推理是通过经过训练的AI模型运行数据的计算过程，以提供AI应用的即时结果，从而实现流畅的最终用户体验。随着AI大模型的发展，实时推理的需求激增。Ross认为，对于在产品中使用人工智能的公司来说，推理成本正在成为一个问题，因为随着使用这些产品的客户数量增加，运行模型的成本也在迅速增加。与英伟达GPU相比，Groq LPU集群将为大模型推理提供更高的吞吐量、更低的延迟和更低的成本。他还强调，Groq的芯片，由于技术路径不同，在供应方面比英伟达更充足，不会被台积电或者SK海力士等供应商卡脖子：GroqChip LPU的独特之处在于，它不依赖于三星或SK海力士的HBM，也不依赖于台积电将外部HBM焊接到芯片上的CoWoS封装技术。不过，另有一些AI专家在社交媒体上表示，Groq芯片的实际成本并不低。如人工智能专家贾扬清分析称，Groq综合成本相当于英伟达GPU的30多倍。考虑到每张Groq芯片的内存容量为230MB，实际运行模型需要572张芯片，总成本高达1144万美元。相比之下，8张H100的系统在性能上与Groq系统相当，但硬件成本仅为30万美元，年度电费约2.4万美元。三年总运营成本对比显示，Groq系统的运营成本远高于H100系统，而且，更关键的是，LPU目前仅用于推理，要训练大模型，仍然需要购买英伟达GPU。创始人为谷歌TPU设计者之一 相信未来2年能卖出100万个LPU在今天互联网上一炮而红之前，Groq已经低调埋头研发7年多的时间。公开资料显示，Groq成立于2016年，总部位于美国加州圣塔克拉拉山景城。公司创始人Jonathan Ross是前谷歌高级工程师，是谷歌自研AI芯片TPU的设计者之一。产品主管John Barrus曾在谷歌及亚马逊担任产品高管。高管内唯一一位华裔面孔、副总裁Estelle Hong，在公司任职已有四年，此前曾供职于美国军队及英特尔。就在去年8月，Groq也宣布了和三星的合作计划，表示其下一代芯片将在美国德克萨斯州三星芯片工厂采用4纳米工艺生产，预计量产时间为24年下半年。展望下一代LPU，Ross相信GroqChip的能效将提高15到20倍，可以在相同的功率范围内为设备增加更多的矩阵计算和SRAM存储器。在去年底的采访中，Ross表示，考虑到GPU的短缺和高昂的成本，他相信Groq未来的发展潜力：在12个月内，我们可以部署10万个LPU，在24个月内，我们可以部署100万个LPU。","kind":null,"is_publish_news":false,"is_publish_highlight":true,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":0},"commentList":[{"id":276233901957336,"gmtCreate":1708470045482,"gmtModify":1708480621745,"author":{"id":"4162268573686842","authorId":"4162268573686842","name":"Kenny Gong","avatar":"https://static.tigerbbs.com/b9454f477643c84a0b7f2260bc2bc8c7","vip":1,"crmLevel":4,"crmLevelSwitch":0,"idStr":"4162268573686842","authorIdStr":"4162268573686842"},"htmlText":"三星？","listText":"三星？","text":"三星？","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":0,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276233901957336","repostId":2412738401,"repostType":2,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"},{"id":276118834811176,"gmtCreate":1708441955330,"gmtModify":1708442093906,"author":{"id":"4089244850507840","authorId":"4089244850507840","name":"发型很乱","avatar":"https://static.tigerbbs.com/0de77920acd17ed185287a92fad15107","vip":1,"crmLevel":2,"crmLevelSwitch":0,"idStr":"4089244850507840","authorIdStr":"4089244850507840"},"htmlText":"明显是小母牛放屁——吹牛B","listText":"明显是小母牛放屁——吹牛B","text":"明显是小母牛放屁——吹牛B","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":0,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276118834811176","repostId":2412738401,"repostType":4,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"},{"id":276105157939312,"gmtCreate":1708438611223,"gmtModify":1708438612712,"author":{"id":"3472642382762181","authorId":"3472642382762181","name":"神刀","avatar":"https://static.laohu8.com/default-avatar.jpg","vip":1,"crmLevel":1,"crmLevelSwitch":0,"idStr":"3472642382762181","authorIdStr":"3472642382762181"},"htmlText":"天下武功唯快不破","listText":"天下武功唯快不破","text":"天下武功唯快不破","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":1,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276105157939312","repostId":2412738401,"repostType":2,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"},{"id":276097944453360,"gmtCreate":1708436853800,"gmtModify":1708436855427,"author":{"id":"45014872579125","authorId":"45014872579125","name":"embcx","avatar":"https://static.laohu8.com/tiger_upload_file_1456326044.png","vip":1,"crmLevel":6,"crmLevelSwitch":0,"idStr":"45014872579125","authorIdStr":"45014872579125"},"htmlText":"对英伟达是个挑[微笑]&nbsp;&nbsp;","listText":"对英伟达是个挑[微笑]&nbsp;&nbsp;","text":"对英伟达是个挑[微笑]","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":1,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276097944453360","repostId":2412738401,"repostType":2,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"},{"id":276094284718376,"gmtCreate":1708435961655,"gmtModify":1708437960335,"author":{"id":"4138773785721910","authorId":"4138773785721910","name":"大内金虎零零发","avatar":"https://static.tigerbbs.com/d5e9be3f382943cf6d4f04fb39ee7600","vip":1,"crmLevel":7,"crmLevelSwitch":1,"idStr":"4138773785721910","authorIdStr":"4138773785721910"},"htmlText":"牛皮啊啊啊啊","listText":"牛皮啊啊啊啊","text":"牛皮啊啊啊啊","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":1,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276094284718376","repostId":2412738401,"repostType":2,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"},{"id":276093745328344,"gmtCreate":1708435827555,"gmtModify":1708435829063,"author":{"id":"3515586475760605","authorId":"3515586475760605","name":"慧_4909","avatar":"https://static.tigerbbs.com/adc2ea5aee7245d4cc04ee6d0fc60efe","vip":1,"crmLevel":1,"crmLevelSwitch":1,"idStr":"3515586475760605","authorIdStr":"3515586475760605"},"htmlText":"牛了老大B了！","listText":"牛了老大B了！","text":"牛了老大B了！","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":0,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276093745328344","repostId":2412738401,"repostType":4,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"},{"id":276091441684648,"gmtCreate":1708435384035,"gmtModify":1708435385448,"author":{"id":"3483952765629229","authorId":"3483952765629229","name":"司徒在广州","avatar":"https://static.tigerbbs.com/464c7a82bebe1a7472e077a46566524b","vip":1,"crmLevel":2,"crmLevelSwitch":0,"idStr":"3483952765629229","authorIdStr":"3483952765629229"},"htmlText":"说说你对这篇新闻的看法...","listText":"说说你对这篇新闻的看法...","text":"说说你对这篇新闻的看法...","images":[],"top":1,"highlighted":1,"essential":1,"paper":1,"likeSize":1,"commentSize":0,"repostSize":0,"link":"https://laohu8.com/post/276091441684648","repostId":2412738401,"repostType":2,"isVote":1,"likeStatus":false,"favoriteStatus":false,"reportStatus":false,"tweetType":1,"langContent":"CN"}],"hasMoreComments":true,"newsSizeData":{"likeSize":25,"commentSize":7,"repostSize":5,"favoriteSize":18,"likeStatus":false,"favoriteStatus":false}}