英伟达下场，首次优化DeepSeek-R1！B200性能狂飙25倍，碾压H100

华尔街见闻02-26

当FP4的魔法与Blackwell的强大算力相遇，会碰撞出怎样的火花？答案是：推理性能暴涨25倍，成本狂降20倍！随着DeepSeek-R1本地化部署的爆火，英伟达也亲自下场，开源了首个基于Blackwell架构的优化方案——DeepSeek-R1-FP4。在新模型的加持下，B200实现了高达21,088 token每秒的的推理吞吐量，相比于H100的844 token每秒，提升了25倍。...

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。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2514856774?lang=zh_CN&edition=full","thumbnail":"https://wpimg-wscn.awtmt.com/158f0d7c-3002-4a68-9a03-92623961aa6d.jpeg","is_english":false,"pubTime":"2025-02-26 22:45","share_image_url":"https://static.laohu8.com/e9f99090a1c2ed51c021029395664489","id":"2514856774","market":"us","top_or_hot":-1,"title":"英伟达下场，首次优化DeepSeek-R1！B200性能狂飙25倍，碾压H100","media":"华尔街见闻","content":"<div>\n<p>当FP4的魔法与Blackwell的强大算力相遇，会碰撞出怎样的火花？\n答案是：推理性能暴涨25倍，成本狂降20倍！\n随着DeepSeek-R1本地化部署的爆火，英伟达也亲自下场，开源了首个基于Blackwell架构的优化方案——DeepSeek-R1-FP4。\n\n在新模型的加持下，B200实现了高达21,088 token每秒的的推理吞吐量，相比于H100的844 token每秒，提升了25倍。...</p>\n\n<a href=\"https://wallstreetcn.com/articles/3741953\">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>英伟达下场，首次优化DeepSeek-R1！B200性能狂飙25倍，碾压H100</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英伟达下场，首次优化DeepSeek-R1！B200性能狂飙25倍，碾压H100\n</h2>\n\n<h4 class=\"meta\">\n\n\n2025-02-26 22:45 北京时间&nbsp;&nbsp;&nbsp;<a href=https://wallstreetcn.com/articles/3741953><strong>华尔街见闻</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>当FP4的魔法与Blackwell的强大算力相遇，会碰撞出怎样的火花？\n答案是：推理性能暴涨25倍，成本狂降20倍！\n随着DeepSeek-R1本地化部署的爆火，英伟达也亲自下场，开源了首个基于Blackwell架构的优化方案——DeepSeek-R1-FP4。\n\n在新模型的加持下，B200实现了高达21,088 token每秒的的推理吞吐量，相比于H100的844 token每秒，提升了25倍。...</p>\n\n<a href=\"https://wallstreetcn.com/articles/3741953\">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":"NVDA","symbol_name":"英伟达","start_time":0,"source_url":"https://wallstreetcn.com/articles/3741953","article_id":"2514856774","we_media_id":null,"thumbnails":["https://wpimg-wscn.awtmt.com/158f0d7c-3002-4a68-9a03-92623961aa6d.jpeg"],"rights":{"source":"wallstreetcn_hot_news","url":"https://wallstreetcn.com/articles/3741953","rn_cache_url":null,"directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2514856774","pubTimestamp":1740581127,"columns":[],"sourceInfo":{"source_id":"wallstreetcn_hot_news","name":"华尔街见闻"},"weMediaInfo":null,"summary":"最近，英伟达开源了首个在Blackwell架构上优化的DeepSeek-R1，实现了推理速度提升25倍，和每token成本降低20倍的惊人成果。同时，DeepSeek连续开源多个英伟达GPU优化项目，共同探索模型性能极限。","collect":0,"end_time":0,"defaultTopTitle":"wallstreetcn.com","property":["earning"],"viewcount":null,"language":"zh","relate_stocks":{"NVDA":"英伟达"},"translate_title":"Nvidia's end, optimizing DeepSeek-R1 for the first time! B200's performance is 25 times higher, crushing H100","themeId":"9b87c04b10a82f84cf5af6d1505b16d3","isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"NVDA":1},"content_text":"当FP4的魔法与Blackwell的强大算力相遇，会碰撞出怎样的火花？\n答案是：推理性能暴涨25倍，成本狂降20倍！\n随着DeepSeek-R1本地化部署的爆火，英伟达也亲自下场，开源了首个基于Blackwell架构的优化方案——DeepSeek-R1-FP4。\n\n在新模型的加持下，B200实现了高达21,088 token每秒的的推理吞吐量，相比于H100的844 token每秒，提升了25倍。\n与此同时，每token的成本也实现了20倍的降低。\n通过在Blackwell架构上应用TensorRT DeepSeek优化，英伟达让具有FP4生产级精度的模型，在MMLU通用智能基准测试中达到了FP8模型性能的99.8%。\n\nDeepSeek-R1首次基于Blackwell GPU优化\n目前，英伟达基于FP4优化的DeepSeek-R1检查点现已在Hugging Face上开源。\n\n模型地址：https://huggingface.co/nvidia/DeepSeek-R1-FP4\n后训练量化\n模型将Transformer模块内的线性算子的权重和激活量化到了FP4，适用于TensorRT-LLM推理。\n这种优化将每个参数从8位减少到4位，从而让磁盘空间和GPU显存的需求减少了约1.6倍。\n使用TensorRT-LLM部署\n要使用TensorRT-LLM LLM API部署量化后的FP4权重文件，并为给定的提示生成文本响应，请参照以下示例代码：\n硬件要求：需要支持TensorRT-LLM的英伟达GPU（如B200），并且需要8个GPU来实现tensor_parallel_size=8的张量并行。\n性能优化：代码利用FP4量化、TensorRT引擎和并行计算，旨在实现高效、低成本的推理，适合生产环境或高吞吐量应用。\n\n对于此次优化的成果，网友表示惊叹。\n“FP4魔法让AI未来依然敏锐！”网友Isha评论道。\n\n网友algorusty则声称，有了这次的优化后，美国供应商能够以每百万token 0.25美元的价格提供R1。\n“还会有利润。”\n\n网友Phil则将这次的优化与DeepSeek本周的开源5连发结合了起来。\n“这展示了硬件和开源模型结合的可能性。”他表示。\n\nDeepSeek全面开源\n如今DeepSeek持续5天的“开源周”已经进行到了第3天。\n周一，他们开源了FlashMLA。这是DeepSeek专为英伟达Hopper GPU打造的高效MLA解码内核，特别针对变长序列进行了优化，目前已正式投产使用。\n周二开源了DeepEP，这是一个专为混合专家系统（MoE）和专家并行（EP）设计的通信库。\n周三开源的是DeepGEMM。这是一个支持稠密和MoE模型的FP8 GEMM（通用矩阵乘法）计算库，可为V3/R1的训练和推理提供强大支持。\n总的来说，不管是英伟达开源的DeepSeek-R1-FP4，还是DeepSeek开源的三个仓库，都是通过对英伟达GPU和集群的优化，来推动AI模型的高效计算和部署。\n本文来源：新智元，原文标题：《英伟达下场，首次优化DeepSeek-R1！B200性能狂飙25倍，碾压H100》风险提示及免责条款\n\n            市场有风险，投资需谨慎。本文不构成个人投资建议，也未考虑到个别用户特殊的投资目标、财务状况或需要。用户应考虑本文中的任何意见、观点或结论是否符合其特定状况。据此投资，责任自负。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"1","news_tag":"productRelease,viewpoints","news_rank":0,"symbols":[],"gpt_button":0,"need_auth":false,"code":"91000000","status":"200"},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":1,"commentSize":0,"repostSize":1,"favoriteSize":1,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"deviceId":"web-server-community-laohu8-v3","version":"4.35.11","shortVersion":"4.35.11","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2514856774","isCrawlerRequest":true}