The AI Hardware Show

## Episode Summary In this episode, we cover: - **NVIDIA Feynman GPUs Push Power Semi Content To $191,000, 17 Times Increase Over Blackwell As Industry Embraces 800V DC Architectures** (wccftech) - [Read more](https://wccftech.com/nvidia-feynman-gpus-push-power-semi-content-17-times-higher-vs-blackwell/) - **Analyst Warns Google’s Intel TPU Bet Hinges on a Brutal Yield Jump From 90% to 98%** (wccftech) - [Read more](https://wccftech.com/analyst-warns-googles-intel-tpu-bet-hinges-on-a-brutal-yield-jump-from-90-to-98/) - **Bain Capital's data center unit removes disgraced tenant suspected of smuggling Nvidia GPUs to China — Megaspeed previously alleged to have spent roughly $2 billion on AI processors for illicit distribution - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.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?oc=5) - **AI chipmaker Cerebras targets up to $4 billion in IPO - ET Telecom** (google_ai_chip) - [Read more](https://news.google.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?oc=5) - **InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper - Formerly InferenceMAX** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/inferencex-v2-nvidia-blackwell-vs) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **QNAP Pairs a 6-Year-Old Zen 2 EPYC With NVIDIA’s 96GB RTX PRO 6000 Blackwell in Its New Edge AI NAS** (wccftech) - [Read more](https://wccftech.com/qnap-pairs-6-year-old-zen-2-epyc-with-nvidia-96gb-rtx-pro-6000-blackwell-in-new-edge-ai-nas/) - **NVIDIA Groq 3 LPX: Inference Accelerator for Agentic AI - NVIDIA** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiWEFVX3lxTE16ZklPT3k4WU9mQ0JTekJiZXVOUXo4YlpUTGFpdHZsMlNUN1IzbUVJcUJKUDFSTXVWczM0ZlEybjhiQ0JtRnRHa3BKaURBcC1PdXJINjZYZTQ?oc=5) - **Anthropic Eyes UK Startup’s Fusion Tech Promising 100x Faster AI Inference at One-Tenth the Cost of NVIDIA’s Groq** (wccftech) - [Read more](https://wccftech.com/anthropic-sets-eyes-on-uk-startup-tech-speeds-up-ai-inference-100x-reduces-costs-10x/) - **Starcloud-1 satellite reaches space, with Nvidia H100 GPU now operating in orbit - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiwAFBVV95cUxQaUtfRWVQMmFwVHhkRVByUGEtbUZuZkRJSHZOUnBXY2VsNzhNeG1PRTJRV2xlejdMQnRMZU50ZnlUNm96MThsMktlMDlSSTVPcm9MNUNOd3FzanNZQmhHR3dSTnNTYjdOMHFTOFBFMXB1OWFUVGpxQ29xQnhucFNJVk9iNUF5Y2YwSnRrLVBVV3YtT3ZMTXhOcXFvNHJlaTJfc1dFMGRqM3o5X0dNU3JNLU5qMF8xNUthYzZUS3RXSkE?oc=5) - **Running AI Workloads on Rack-Scale Supercomputers: From Hardware to Topology-Aware Scheduling** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/running-ai-workloads-on-rack-scale-supercomputers-from-hardware-to-topology-aware-scheduling/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Google's split TPU chips signal shift from universal to specialized AI accelerators - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiiwFBVV95cUxQU2hWcF9XZWdZdnZTVFlIZEpUVDAyYlBhLTVkbldPUDRENkxOYnBfSnpFMjJLT2lKMUtDTEdYMlZ4d1pacVRQRkZpVXBvV3Rmd2lySmJEZERuM2xQYXNVVWdXVk9xQ0UwOXFVVF9tUFNOSnZXVktXRzZNbFpEWXRRUzhvVXVvRVdFY2VR?oc=5) - **Nvidia says AI cuts 10-month, eight-engineer GPU design task to overnight job — company is still 'a long way' from AI designing chips without human input - Tom's Hardware** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiuwJBVV95cUxQYVZfd1NPM2ppd3Exd1dqZllwanllLWVndjJaakJ2Zk1NT09oYnc3X2t3UEhHd2JkUmxPZWRNTnB6aVlaVWhhcFNkelhubzhaMVMyU2ZuZ3NKNTlQX2tHa3BYV29FVDVNblVLZ3RMVHhYelRCMXgxSV9GQ3l5YXZTcWkyQ1RPNks1WHZzUE1NdjVCeV9Vd19DQXUxM0FoakMxWGRtUE1PU3NGUjgtQmNfR3MzUDRUT1hDVXVfSDFVMV9NZUd2eVFJcVJTTUJ6bUw2Sm5GcVZtYzUtUHRyZk5NRVlfR3cxZDZzUXZ2dE1rN3BTUGwtX08zelJrS3pyMlAtU2ZTOVVjZGtEU2Rya0JWLUlwalk5WE9ZdnBZY1ZlNTJzbk15enhSd2tqb1FtTWxERDBIQjhuQjVYUVk?oc=5) - **This Light-Powered AI Chip Is 100x Faster Than a Top Nvidia GPU - SingularityHub** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMipAFBVV95cUxQTm9hQlN3ZGVJemZ1RVBQNUNtM3RJdUQ0cFJ6LU1xNDYxLTBXdnVCM1VvMUViMGlyTlNmcDVnd3kzakRNZV8yWXhpcFhVZzJqRWhveG5yR0RSdmh6TGRGRU54MTBwQnh1LUpkUzcyLXQ0NUhXeWVSZEc2dGxoUDhJZmNUa0FRQS1JNW1FcTFfUjFaZThsM1BUZjc5eEFaelM4UGhQWg?oc=5) - **Nvidia Eyes Bigger AI Chip Output After China Orders Flood In - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMifEFVX3lxTE5waE5yNlhnQlFJWlR4dVNBOTZ2RjFuelJjVUItbFpLWUNRSEotREFjN1RVVXhvdkY2RE13QWJPajR2SlQzaE5nSWo4a3EyaHRFSHVBZnI0Z3NyQkdXeWhiYjUxRDNGQ3FNOWxkZnZEb09IcmxkQWFnRG5acHA?oc=5) - **Nvidia says its GPUs are a 'generation ahead' of Google's AI chips - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiogFBVV95cUxOVG8zU3NmR0xkeDlaMmhNQThNZnN6MFZtV2VfbnNMT0ZYcVJFLUJiaENlTlRGNE9KMXZSdDhMZVdyT24wcE9JdWxJTWNVSFJpOEU1Vm03aXZwT2ZONnh5S1ZBeXFOOERIWVBBNlg5WnBPTVBfM2VSX29maU5UN2h2amlRVFIwN3BXdnNrVDItWHZaSDlLX2w2UF9TQzVUYVd5QUHSAacBQVVfeXFMTm9EMGExa2dMN1pKMWQ2MjZUc1hST2ZCNnFsYTFENlItc3plcm9rdjd1Y3RjLXFQZ2t2V0ZKWW1tLUNwRTRUZW1LbkpkR05JcnNteFk2MUNfcWFWZmJnQWp1RnVISzJMS3UwUk1SQTF0cU5welZqVVdvTElyS3dvS0tpVUlYOXNUOXRuREFnNG4xbzNORXRLaEtpSW1qSWtJLUx6bVJzeUE?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Intel’s EMIB Hits 90% Yield as Analyst Signals Foundry Breakthrough, EMIB-T Scales To >12x Reticle In 2028** (wccftech) - [Read more](https://wccftech.com/intel-emib-hits-90-percent-yield-signaling-foundry-breakthrough-emib-t-scales-12x-reticle-2028/) - **Semifive Wins 3D IC Turnkey Design Deal for Edge AI Chip - thelec.net** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiZ0FVX3lxTE4xczBFV1NldEswY2x6V0NjQVVQOFZhVDFmckp2Q0Nid0pXbjRBSzB1UUVsNV9uUENQWXZPVmoyQ1QtZFI4Sld4bnlPRzV4YUozZjhmYXlDWnBvYnNyT3FwaGl0MC1aSWM?oc=5) - **Nvidia CEO says Google's TPUs pose no threat as AI chip race heats up - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijwFBVV95cUxNQXMxYUZVNHdiZ3VncThEUEczZkszVFBWY3dleEtJT3lqTzE1c3FtVjNOYlNMVmlybXBZYktqZDNlVlNUMmVraWlpbEhYTFFXdEtDNzFqenIwcm5jbkdiVDRRWEFSTFZtTTZOdVdrbWVzT3FzbTlobV9LQWhIdGxoZDNiU1RwclJCY194akhYMA?oc=5) - **Chinese GPU maker Cambricon's Q1 revenue hits $423 million as country's homegrown AI chip market accelerates — Chinese chipmakers continue to leech market share from Nvidia** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/cambricons-q1-revenue-hits-423-million-as-chinas-domestic-ai-chip-market-accelerates) - **TSMC posts 35% jump in revenue to new record high as AI chip demand stays strong - CNBC** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiiAFBVV95cUxNTXFOajBvclRZZ0Nxem9tYThILUkwVWRHLTRWMTB5aDNySFM3RHlIeUxvdFNUbGtXRnEySUtWQ0M4RmFWR2hLUEFUTjUzaUdNOVlySWFMZHpIUWU1U2ZMdEEtaHJ5WTE5MXgwR19DUFVwREFfSVF4U05TZk5aVmgtanRySW5OMklP0gGOAUFVX3lxTE11Ul9BWEVTUzFWcER2YkE5SUM4Z09ZV2xNRU82Qlh2Y241ZlZrT242R2F5UENuTFBwTXhaeVNzcWxtX0E2VkUyRVMwa2VWU0pnVVZXczhUWk11U2pReVU4XzV5cHRNWU1mY1BhbW5RbEFnZndNR1FCOGlsaUFwSE5MdlBtZXZsRkktaVk0U2c?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Google to sell its TPUs to some customers, who also fancy big-G GPUs** (the_register) - [Read more](https://go.theregister.com/feed/www.theregister.com/2026/04/30/alphabet_google_q1_fy26/) - **Nvidia announces Vera Rubin Space Module — up to 25x the AI compute of H100 for orbital data centers - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMikgFBVV95cUxPNW9yQnZ2eFJnR0VsNUFjY2xSd20xNGFxTkVNVkpxc1BrdXhoSFBUdkZqeVZ4bnJxR3NlVU5qd21PNVk1LVRqNldkcDdRdzUwR1JpVDdGemlxZWN0S3RYV1ZxV0NnTThEcGQ0MWo5WElhZW5YdExOY3YyaG1pMTRLUHdKSUZNMXc1dVpBYzRwdXBqQQ?oc=5) - **WAVE-N Specialized Video Processing NPU for Edge AI Systems** (semiwiki) - [Read more](https://semiwiki.com/ip/chipsmedia/367442-wave-n-specialized-video-processing-npu-for-edge-ai-systems/) - **Data Center GPU Market Size, Share | Industry Report [2034] - Fortune Business Insights** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMieEFVX3lxTE9ZOEhOLVRsLThWdkhVZ3hfaG1xV1ptekhLVFI4ajB6X0VWcWI2cllzLUFZa3FhbGlDSEtDY0kyNHpwb25uMWdUSkp3ZUN5N2VrelBORkFBTXRvYjNrWE9ZM3Q2TVNZdExZN2haTm40MnNTNFhGd0ZOUw?oc=5) - **Report: Samsung Hits 80% Yield on 4nm Process as NVIDIA-Backed Groq, IBM, and Baidu Pile Onto Its Foundry** (wccftech) - [Read more](https://wccftech.com/report-samsung-hits-80-yield-on-4nm-process-as-nvidia-backed-groq-ibm-and-baidu-pile-onto-its-foundry/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Top 10 Data Center GPU Market Leaders & Trends to Watch - Kings Research** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMihgFBVV95cUxNTFFtRFRYa0ZUN0xvME9zS0FMbkZnLW9NU3BqMHVVNmFsMHVDRFphR2hnODRzbHFSV1ZjN1A0ZlFQeXFsTUQ4MUp1dTk4dml6ZUp3dUhXeGRSLW5SWDR0d19tUjZZRVJ6RkZLYlZ3Z3QzajBmbFY3N1B6b1gzQ1JJM1pEZHU2UQ?oc=5) - **Intel and SambaNova Advance Agentic AI with Xeon 6** (intel_news) - [Read more](https://newsroom.intel.com/artificial-intelligence/intel-and-sambanova-advance-agentic-ai-with-xeon-6) - **Inside Google's TPU V8 strategy, delivering two chips for two crucial tasks at incredible scale — network scales up to 1 million TPUs per cluster, an advantage over Nvidia AI accelerators** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/semiconductors/google-splits-its-tpu-into-two-chips-for-the-first-time-with-training-and-inference-variants) - **NVIDIA Hits $5 Trillion Market Cap on Soaring AI Chip Demand | 2026 Analysis - Intellectia AI** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiggFBVV95cUxNOVdqY1ItWjYxRTJnMVU4X3luSWJGUXlZRkVybHRHbXZ5YkJXNGhzYzdZb2JIZnM0YWdkZkVZVUtHbXNiRkRDOEZqX2ZVRzhQWmpxSjFLMmY2Z3NhZzdINHk0ZV9LUmFsUTN6Y0ZPcUItYjlySTVJYjB3OHN4YmsyZHhB?oc=5) - **TSMC to boost capital spending as demand for AI chips surges - Financial Times** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMihAFBVV95cUxOMlhESm14cGR5dlJzTGVwck9YWEtEUVFjVWdOMzluOFlPekxOS3dHZ01vdUpWVFhXQklrRXlpUENVMnRjNkZIRVJ4YzZXZGJRRFNnTC0wNVJMRFRkVEdEUGlJZDJFOTRmUDFwaUk4VVdQcWZ1T01xb0pSVjg2RUU1TVZ0QmY?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Cerebras files for IPO after AI chip breakthrough, G42 partnership shapes supply chain - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijwFBVV95cUxQZC1uWTJ2U0VXSXlKWGdFWHRXMHQ4QWtnZDZsaGk5MTZzcHdKNy1Fb0NTT21UNnpZaGRfYm5MazFoellYX3VzNVZfeGtQOTJVM0ZESDdwZkViRGJwR1hzSFRnekZYUXRONWJVdTRQWGdBT3lVajRsZVJMQUZIcXdNZlRxV29Xelg2RlQ0NzNoYw?oc=5) - **TSMC and the Battle to Cope with Surging AI Chip Demand - Technology Magazine** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMicEFVX3lxTE1sVzQ4UDNLc0lybGlqQTVnV1lFby0yVElIQ1N0Z2FBY2IzS09QeG42Z3ZCNHIwS3hfTm13WU9xaFB2NVJRT3lKcVNxSGx0eEZ3bkJPWVp1T1pVc1pVNVEzNGhpU2FETXhBQmM3Ukd5UlY?oc=5) - **TSMC Stock Surges As AI Chip Demand Breaks Records - Evrim Ağacı** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMijAFBVV95cUxPaVY3QWJpWjIzRktKQXpuWlBUNHZoRVp4Z2tTU0ZEcGN0V05SdXBHSUlhdFgtblp4a25Dd3dYdVRWS184M0FGd294RUwyU1hpRzFCV3B0M1MxUFNKSWNNZ01fanFLOUVMLUhwR1lJOU96RkdjbVVWQzJ5WHlJZHRSNi1rLUFpeVo1VnVDeg?oc=5) - **TSMC's details next-gen CoWoS roadmap: over 14-reticle packages and 48x leap in compute power expected by 2029 — massive size enables 24 HBM5E stacks and additional memory bandwidth jump** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/semiconductors/tsmcs-details-next-gen-cowos-roadmap-over-14-reticle-packages-and-48x-leap-in-compute-power-expected-by-2029-massive-size-enables-24-hbm5e-stacks-and-additional-memory-bandwidth-jump) - **Nvidia launches Groq 3 AI chip and CPU server aimed at Intel during GTC 2026 - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMivwFBVV95cUxOcUZJSWMwR2VRS2JPYWo2c3kyS2J3V1l6OFN1NkJvbGhaWG1GekJWbk5nUV9YbGdLZ0dxMFZjT0pRd3FPQllmOUVjbnJmMkVhemQxTzhpdEQwY2JKX05wYzQwLWlGM0F1SGVuWEVWd1R3VFlobXdnOW4xRzdoVGJBTUdONlVJX0pocnJ3VlJyZnhXSWlfNV9pSlphUG81OVJ4dXpjNW15ZlhxLWFpVFA2NURYcDF4clJUa1c4ck5FWQ?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Chip Industry Week In Review** (semiengineering) - [Read more](https://semiengineering.com/chip-industry-week-in-review-135/) - **NVIDIA Grace CPU Delivers High Bandwidth and Efficiency for Modern Data Centers | NVIDIA Technical Blog - NVIDIA Developer** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMitAFBVV95cUxPMmJWdFZ0T1QxNWUyWDc5NVduNklwV0JKWTlsTGNJeWV6S2NlQ25vbDRuZ2lLMmhKSmJVaVdJeXdRSzhGLVd4WTlkM2lRdVBEUXdXS2laejNzemNiUks1OEo3LVZ6SjFpbkMxMEtjWWxyZnJ1QUlfc2owNEtBeEM2VGpXMkJrekZHOU5QU0x6MllUY0Nfb18xOHNIWnFDT0Z0aHJhd0h1QzlxZDRTTHd1S05RNGk?oc=5) - **Cerebras Systems Files IPO, Pressures Nvidia's AI Chip Lead - Let's Data Science** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMioAFBVV95cUxOZldYUFlTcjh6VHI5aVlWUlI1NkdjUjFDZVA4a2tPci1iako0c1ZvR1lyd0M4V3NtVENrUU9oM1dQZjhiSThMbEpxZlVVWFFhRlBSU3h3MkRjTnhMeXRobVBXdWo3Yy1iajhIdDBpNUZpNm9GZ2ZEY0NOb1hEQjBOM0pxc1Y0dlRRV3F1ek5hMU9EQk1Td1ozWFdGb2VmRGZu?oc=5) - **E2E Networks acquires 1,024 Nvidia B200 GPU cluster for Chennai data center - datacenterdynamics.com** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiugFBVV95cUxOR29qZVM5SkFFdjBIUmlQcTNFejk4eHJxVklNMVo1d18yRmZpTUtHdGN1Zk95V0hEN3VieGk1LW52dHB4TzhrUzdNZFFONU9hWnYycEN6ckc1SXZLcVU5OEw4OUp3TC0zT0trZUhYSGI0X29MTkd0WllnSXR6eFpkbnd1Q081OEgxeERMLTdLeVJ2MWR4bW50MHBrNGZKbnR1QjlqOUY2RUQ1T3h5bFFhcDNEZl9LbmM1aUE?oc=5) - **NVIDIA Supplier Taiwan Semiconductor Is Winning The AI Chip War — And The CEO Just Told Intel, Tesla Why - Benzinga** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMi7wFBVV95cUxOcnRubUZVTFFWQ0w3UGhuMzhkaDhBRU1lS3dmNXRGTTNYV0dBRDBRQXo4bnlzbi11Y01JMlNjVFBnUDNHVWJjZXdlVkFrRWZCdlB3dmYwQWNPQlI4RVFNNGxGMVBKTnJBQ2tqSmVyS0xUMkZ5Ym0wTW5ZZVVjeGtJaWpSQ3lUSjNRUHdBRVF5QXYyRFctcmpSU2ZpdUp1OXB5a2NBNmR5bDdWRGxjRWtmU2tQZ0VHSkJhVENPaHhsTnZTU2txU0lJd2lyZWMyVUlacDBPZU12dUs3ZmtmVEl3MTJLbmhlMnFHMWg5OW9Ocw?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Meta strikes AI chip deal with AMD days after committing to deploy millions of Nvidia GPUs - CNBC** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMipwFBVV95cUxOc2ppUVhkZU03cXN4cUNwS3RXdEJJcmJST1RBUnBIcEhOd1E0VFBNekFoVjRKelJGeWEwckZlLXVJVGY5TEpiT0dELU5aaG0tNktmbzF6bXNXclQ5Q1E4SDdWM2p1UXd6NzJ1dWF5MFhnN1RDNDVpdTFqUmhLaU5ZMEdIQ3Rnbi1lZ0FCNVhET25sblVxSlFZTjU4RzZzLWhDcXFRUFJmWdIBrAFBVV95cUxQbU1GQm44YUdzT19wdVhFS1A4N25LMnp5NmlnMS1vZEZLdktUa2pCNlRkOElYYnNPSGxTcGNKeHA3QktGc0ZNVDYxTlNEZ01GM1phYUMwWEprU2htcjltSEFJa0FLLUkzZUIzN3F6N2NnTDNqSlZBVk9xYXJfM1M5d25TOGJaM0lHcURLZllvUjFUb1M2ZC1rMUFEUjYxcV9rdTdwQWg0cUtUSEpy?oc=5) - **The great data center delay: Why your AI chips are stuck in 2026 - Manufacturing Dive** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMilgFBVV95cUxOQVpWcE1vRTVLbzZ2TUJUeml6SUF0SGY5aG5wVWVZUlRWdGJwMHA1djBuMm1KejBpZmlUTXlkWGJlN2J1ZVBhQm1CZDlLTW5pZ2ZtSGRJcW12dTBjcks3NFhNUGpJZHE5cXI3VEpZVUIwLW5VVGlGM0pmSkd1b1hTN1hlQlZmYUxsTGZveUFZaUU0eUx1b1E?oc=5) - **Nvidia Brings Blackwell GPUs to Enterprise Data Centers - Data Center Knowledge** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMirgFBVV95cUxPV0NWRV9oRDl0YzB6UDJxV1ZaUjk0WmlFTFVoNExMMjJNTEFobjdqdzR1M2tobUw5QWNWNEhJdlp0QnB1alJyZUFOTks4YkF4STNUUGZxY19KZHU3RklJSjhNMHdwYjdwSmVMdTFUNmxPTGZna2Z3aFB5N2FuOURScEZZMUZJWVVBWFVQbDExT1pRcmI3MGdYMlFZVXdFU0h0R21hNzBwLU1IMXZoZXc?oc=5) - **NEO Semiconductor's revolutionary 3D X-DRAM for AI processors has passed proof-of-concept validation — company secures funding to develop next-gen memory HBM alternative** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/neo-semiconductors-revolutionary-3d-x-dram-for-ai-processors-has-passed-proof-of-concept-validation-company-secures-funding-to-develop-next-gen-memory-hbm-alternative) - **Meet the Biggest Threat to Nvidia in AI Chips. It's Not AMD, Intel, or Broadcom. - AOL.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMifEFVX3lxTE9lWW4wejk1QldjNkVNN2tzUDR6VDBITlhxT0RXb2lsUmxRTWRmNnBESnI3Z1JsQlJlU0R0WUFDazE4Q2h2VEdqUEpISEwzcmdlcWZFckRDQjI1ZWQzSTVUQkpNekQySzVtMWhQbVNTc0IwY1JLdnlsT0c3N1A?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Siemens and TSMC Strengthen AI Chip Partnership to Accelerate Next-Gen Semiconductor Design - Bisinfotech** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMivAFBVV95cUxPNG1mTVZRbkpUc1IySTVtcU5weDUyZGdWN20ydGFSTlh3cGQwOGRXem4xX0ZzbkdzOUE2MHNkWU0tZnVrZnBNLUhmOTA3V0xoN2JOMlg3OU9JbkJHSDZxUnBaRk5wTUx4ZS1xWTEtREVhMG9JTzFsS0c0bThGakJIVVpWa1ZFZ2ZzMFo5YnFXV1RRYVpob0lVY1Q5OGcwcjZyOFlGeG1uVExBdDRUVlJJRmxOOEp1MHJrLVZMaA?oc=5) - **US semiconductor reshoring efforts collide with the AI chip boom - Sourceability** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxNdXFUOW5WUXNPN0pXYXcwYjc1LVItMlREbGdieThvZmFYamlkZ1VuT1RuOFhfYUJsS0pyalRFanRsNmdjbEViS0N5eTlyY1VSdHVwOWRYejFkZ0toWFlYbmpldmJSV3JqZGhTclFfdVFHNDVDV0t3M2ZaMmZ5MTJadno1N2JnaUFRZXdZVzBlWU5yRkh1?oc=5) - **DeepSeek's new models are so efficient they'll run on a toaster ... by which we mean Huawei's NPUs** (the_register) - [Read more](https://go.theregister.com/feed/www.theregister.com/2026/04/24/deepseek_v4/) - **Groq’s Inference Chips Are Beating NVIDIA’s Blackwell by 5x on Cost – And Doing It Twice as Fast - Wccftech** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitwFBVV95cUxNYWQ3WUxyczZJSVpSeGJrSmdIaFBQZEZXcHk1M0ZQTGNlVWt2MDVsanoxWEZnYUtCV2d4WThvdlVhWW83ZVJ6NWc1bHZ1NkV3TkZkSDBVS29PRGFYb1ZaQ0t3VFV3cnVtbUZmYjV2dlRvZlZ6Zm5pVWNrVXgzUkd6bFEtQ0M4WmQ2MkdpbUEzQ0FKY2dSYUE0a2JrYTZ2SW9YOVZDRW1TU2ZCM016TkxqcUFrYlVUMlnSAbwBQVVfeXFMTWZLaDB5Q2ZvLUNabDhfVWlCWHJBVjJoeS1ENnIxSnBZS0VPZjdFM2N4OFFyVzVEZ2MyVWFQMlYtOGJISVlfb29teGVmM1hlV1ZMRnNUMTlONjRnSTFscU1OeWs2Zi1XaXRSN1JqekphSThXZlYtMGpPUHN6OGpEa0gydnBkRm94dTdJYXdpQnl0VlYwQVZGUmRjWDlWV0pHdmFieGR2VzNIamlqVmRFM1ZEYVlaaG1SaW9SbWg?oc=5) - **Vera Rubin – Extreme Co-Design: An Evolution from Grace Blackwell Oberon** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/vera-rubin-extreme-co-design-an-evolution) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Google reshapes AI chips as TPU-CPU-cloud stack challenges Nvidia - CHOSUNBIZ - Chosunbiz** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiekFVX3lxTFBiN2tFNW52aG9jcUtJMXY1UFhSbFlpbmxaX0JTN0twN2lUX182VlZ4SXh0aXFNVEdIZkFfQ2VIaUJUbGxudjliNUtlZWotYndlcmtHeUVoR2ZaSWpMVDJCME8xYXJjakNfYTdpdGYwaTEyTHBNdHRzZXBR0gGOAUFVX3lxTE0tOU1pQUg0MW9NTEhNeUpsbzUwc3RibURXZFhJaGp0NVp4OGtCa1lnVWlYMFJaTjh5UXpDR3BDLURhcFhaZFB3M0lkYnBMMDI2bjBPV3JicTFVdzB2UlhOMWpVQXQzN1VMRlF0dUFKSUFBUmtfU05yaHJ0NTJpb3ZSUHZOTDFRSVAteDQwc0E?oc=5) - **NVIDIA RTX PRO 4500 Blackwell Server Edition and vGPU 20 Redefine Data Center Virtualization - Technetbook** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMihAFBVV95cUxOa3lsaXdPeWluMVZmb0RQT3hKNUdJWmtZdUlnUXJGUG9HWS02ci1rMXVjOWNkdE9GbHA4ZWJ1QnlMVmtrbmlYd04tdXNYZ0xfMk9DMEVfR1pFYzNRdk1kbXhHZnNXa0RySzBUZ2hzN3FOZTNEbmhaQzREVjlMQ01OSUtRZjI?oc=5) - **Google Unveils TPU 8t and TPU 8i: Direct Shot at Nvidia AI Chip Monopoly - techi.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiZEFVX3lxTE5VSVl1YnAwV2czRWlVWVdwS1VucExiUWxmRzhNSloxeVAxcG5uUEFOLTRoS3BrVXdTbzlTLVhjQXRmclFuNFhBVFVabDZTMVVQNlJPU3l0OHZsZk1YSVQzb0dQMEY?oc=5) - **Will Google TPU accelerate 'AI Market Chapter 2' again? From NVIDIA GPU to 'optoelectronic fusion'—the battle for inference supremacy and the benefiting stocks - Moomoo** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMirgFBVV95cUxQSzFFM014ZTRKeTlReDZRQTFsdTVLcjJDLWVDMGpLOWRhNzdrTUJHR3duSjA0bUtPblI2ZDN4OU5sbVI1N3hacks3UFBIYVRtZUlVWGJmV0V4RE16aXRBZmx3Vk10Y3NvN0kzUEkycXFPS3ZZYWliRVlFTGx6RUxxSGhZVUdMRUJJME5BOWFLT0xJUXN5NjcyUksxSmJMVGNfa1pXcUx2SUtCX1ZWTFE?oc=5) - **SK hynix PT7 Advanced Packaging Mega Plant: $12.85B Bet on HBM Memory, AI Chip Supply Chain, and the Real Reason GPUs Stay Backordered - Intelligent Living** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMie0FVX3lxTFBjZDRKcFRIQU0xTVYySFd1dXVjbWRKZ01aWjg1SkI2dUFmNnFDS002Uk5LYnlobjhZQUJwYjF4MnRmMXlVazdWaFQ0ZnowSWE0TzI0SFJKclJ4cG9tVnZKXy1LQlI4cWZWa2JzZDl3UU1adWRDWlRxVVdlTQ?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Forget one chip to rule them all: With TPU 8, Google has an AI arms race to win** (the_register) - [Read more](https://go.theregister.com/feed/www.theregister.com/2026/04/22/google_tpu8_dual_track_training_inference/) - **NVIDIA vs TSMC vs Broadcom: Which AI Chip Stock Looks Best in 2026? - Gotrade** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMijgFBVV95cUxOaE9Rb1B0UXpDeGxlRlVYLTNxX2RINmo0NGRCTE11XzBqQTJwMHRhbFRwWmIyT0Y4YlI2TWlaZG5haGZlMDdDc2g4cHl5RTU0aUJtZjc5eHV1dnZBb21lU3d6RWIwckxmX1V4Tl9LZ05RTHBWaUU0cHBiT2RCSXZhNlhJeTNtYUhxazBIMmFR?oc=5) - **Nvidia's H100 GPUs are going to space — Crusoe and Starcloud pioneer space-based solar-powered AI compute cloud data centers - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiigJBVV95cUxQZllrWXhKMTBZWl9GaHJSeVZrMm9Wek00NU83dkxRTjcxazd3eW9YRnlSb0dNSWxxSmd6TWpGU2l5RnMxY3J1a3RSbEZVNDJTdFB2ZTVHUkdHTjhPUFJZZ3RZVmE0cmdnM0J5cXNoc0VoOExVcUVrZW52TW1lX1U0RVJocFFNS3hoVzVCZk9PQ2FGY3pDZVNqYUxLQmlqU3lqYzlKQjhvT09NUWVfNG52UWNGMEVhYTQtSkhuMVZ3Y3JPbXVHYUtaRVZMeS0wMVhGeFdzRS1KbGFqdDJ4U0tIMnozZEpBLW9MY0ptNEQxcGpDWGFYd2EtV2FQaUlGT1ZoTmRrYTZ3RmhRQQ?oc=5) - **Google TPU 8i for Inference and TPU 8t for Training Announced** (servethehome) - [Read more](https://www.servethehome.com/google-tpu-8i-for-inference-and-tpu-8t-for-training-announced/) - **Scaling the AI-Ready Data Center with NVIDIA RTX PRO 4500 Blackwell Server Edition and NVIDIA vGPU 20** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/scaling-the-ai-ready-data-center-with-nvidia-rtx-pro-4500-blackwell-server-edition-and-nvidia-vgpu-20/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **E2E Networks acquires 1,024 Nvidia B200 GPU cluster for Chennai data center - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiugFBVV95cUxOR29qZVM5SkFFdjBIUmlQcTNFejk4eHJxVklNMVo1d18yRmZpTUtHdGN1Zk95V0hEN3VieGk1LW52dHB4TzhrUzdNZFFONU9hWnYycEN6ckc1SXZLcVU5OEw4OUp3TC0zT0trZUhYSGI0X29MTkd0WllnSXR6eFpkbnd1Q081OEgxeERMLTdLeVJ2MWR4bW50MHBrNGZKbnR1QjlqOUY2RUQ1T3h5bFFhcDNEZl9LbmM1aUE?oc=5) - **Nvidia gets Beijing's nod for H200 chip sales, adapts Groq chip for China, sources say - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitAFBVV95cUxPNEVlQjZrU1hSX09aM1FEZndmSzR5RVFkejlDaVpUNGd2QkJRMG1fVkNKaGFrMHRFR2doTXhPUUQxdFVZeW5felVvOGR2bDhKbjMxTXh0ZHU1aHpQdEJ6ekFmc19ldHMzWUxkUW4wNFRLNlhYZTVHTUM5NnBNVFlMU3VrUjBjWjROUzdkazI5eXBYWUc3TlIweUlQV28tdldQdm1GMnRuZEtFbFRjLTNGTHRjajM?oc=5) - **Dissecting Nvidia Blackwell - Tensor Cores, PTX Instructions, SASS, Floorsweep, Yield** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/dissecting-nvidia-blackwell-tensor) - **Nvidia Debuts an AI Chip for Space-Based Data Centers - PCMag** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMikwFBVV95cUxOTF9LcVA4dlU4NFVLejV5UDhwU05iZzlZTGdXMEtZdzVueUFCNzkzcFFhZzVQWmFlbHhRZllUZ1ZMNklaRFF2ZUx6U0ttY0hRcklYLXloaG1rd1Q0dFI2RHphQ1lmTmdFQTZoanY3MngzNFJUNU9NeVUxUHFYWmZfX1VVam82S2c0R2pydmpSNlVCYkU?oc=5) - **Nvidia to launch AI chip for data centers in space - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMinAFBVV95cUxOVl94UVFMaFhJUmM5aWM1QlRRajRVTHU0SG9ZNG1vMU8xVk55LTRtdDFFZFlXREd3akRwYThWVVk1WFdwTmNnRzd2RWNXR3JJRUVhck1BOHk5b19jSXZnSEVsYlF2RmZhdHdReEotZ1ItWkkteDRENUI5Sy1TNTZocWJsLWlVNUFJZ1B5dnYzYkh5YmJESTR1S2U2dkw?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Cerebras Files for IPO as It Takes on NVIDIA in AI Chip Market - Mugglehead Investment Magazine** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijwFBVV95cUxQWVJQR2c3UkNVYjAwbzBCX0dTOFhrVDJBcUE1blBCMUxzWk1GMnlRVmJvaTl3YmtuQ1Y5d3AwWF9MVlFoRi1WNlJuUHVRaWZUTkUxbHhMb3V3YWpzdElFdjM1SWF6YmtlWG9pUktzVzVDUnVYUHF1VjMtUUtCYjkwLUJ0d2EyZzcwa0xsbk1taw?oc=5) - **Google Taps Nvidia Partner Marvell to Develop AI Inference Chips - Seoul Economic Daily** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxOUlZ2eEkzXzc1OGNHa2tGdlhiRUppWHVqczRQMGllQzhXbzdkWGh5RjVQTDY0MjVibExQZnJDeWZleXZ4UHFOTDJsYmpPTlhnSGswa1FwaUR1RGUxZjJNMkFWLVpUUkE1Qnd3aW1xaHdacTBxcTBpZGh3b29teG9mb0szdG02bmlnS0lvYW9DWkdjcGxvUGRRUFlXd0xpdDBNMTh6aUVTWHZSQQ?oc=5) - **Meta expands Nvidia deal to use millions of AI chips in data center build-out, including standalone CPUs - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTFBiLXZYX1ZjaTRaenZCcmpJT0FZTksxVFpNOWhYOXBHenZDUjlKLXBoTDJuOHluYzRiSWx0YVV6Slljb3NBem9CLVlJUHlTR1FIQk15ODZGRm4yaXduckZ6YW9DNTJoYkZveDFwS3Y1amFOTkRiSi1lNDYxZlQwMFXSAYQBQVVfeXFMTVBJeVBlbFhKZDhpWE56QTZ4VDFJYjlrSk50eFgtQzViYUduMHRZRmJ2amNRdjZDeVFmUnpfNE54LUhqR2ZTSWR0eXBDcE13Q2wxekszejRCTFlKSHRZWDlWZDgzb0pqZjE4QTdrd0FhZDhQSTNHWDZDMlQtNUYya1RTVkJO?oc=5) - **Cerebras Files for IPO Again. Its AI Chip Has Big Backers—and Big Risks. - Barron's** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiggFBVV95cUxNdmpUeUt5a1laMlE2Wk5RdUp0WTNFSUwtRHpzMkdpWGhNd196Zmd6NUtGQjVSZ0k5aVFuWXAzQnJkM2JJUzNHS3A2eWUtRVNVQ0tvSUprWFY3U3plZWQ3QXBkaTh0Nlh5NVBvazdQMGZ2WjBNZDBhM3Frci1VVE92ZUpn?oc=5) - **AWS Trainium3 Deep Dive | A Potential Challenger Approaching** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/aws-trainium3-deep-dive-a-potential) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Bain Capital's data center unit removes disgraced tenant suspected of smuggling Nvidia GPUs to China — Megaspeed previously alleged to have spent roughly $2 billion on AI processors for illicit distribution - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.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?oc=5) - **NVIDIA Leads in Data Center GPU Market: Will Blackwell Keep It Ahead? - Yahoo Finance** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTE45TU1qajRialRGMU1qZTlGMWVQSFlsUk1STlFiZ0o5ZnBiT1hMdWZwZGNhR190RWxBREx2bXZGUXNONVMwQUxlMTZuaHZtZUZLT3lkYlhhMGN2U2V3ZzJnTGhuaGR1Xzd6MWJtSTRyU2p1a1QwYVZMb1FDWEszZVE?oc=5) - **Scaling NVFP4 Inference for FLUX.2 on NVIDIA Blackwell Data Center GPUs** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/scaling-nvfp4-inference-for-flux-2-on-nvidia-blackwell-data-center-gpus/) - **Trump greenlights Nvidia H200 AI chip sales to China if U.S. gets 25% cut, says Xi responded positively - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMidEFVX3lxTE5aS194WTh1V3I5MlNzUkthMTl0cDJMdzV3UkxxX3JPX2p2SlFsLXJZanNaUXZfc05OTHVJalI1aEt2TXZRR1J1RGNrWmVJYm9Jd1FGOFJveENudlNHVjFNX0p3S0kzR0UtRkRyTGZXRy1QVWVJ0gF6QVVfeXFMT1NmclpBWFFJaThZWUFJd0t5bkZ2SzBTeTRHbGhtbzVJLU5TVlJCaXBlbGJYU2xtM0lqbXRRcVlPUzlveEE4VXFTT182RFZPVXhxSExPWU8xZ2pyNzNEVnQ0cXpVXzlBQ0lnRzdLU2hralFfSllCZTJGZ2c?oc=5) - **InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper - Formerly InferenceMAX** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/inferencex-v2-nvidia-blackwell-vs) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Running AI Workloads on Rack-Scale Supercomputers: From Hardware to Topology-Aware Scheduling** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/running-ai-workloads-on-rack-scale-supercomputers-from-hardware-to-topology-aware-scheduling/) - **Cerebras Files for IPO as Demand Surges for More Efficient AI Chips - WSJ** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMikwFBVV95cUxQN1o1WkloLUZqUTFnYTVVVU1wc2o0cDllQldqOGV3R2lsNlJKNDQzejZOa2lMWUk5ZkhCVDZ3ZmRSZUc2cTFIb1BMcU1RVkZzbFV0WXR2U216bTdiUlZCZzEzREZTRXpKVHlfSHBCUHFFRnhQNXd0dGVMSjZvSkRFMlY2MXItUTVLeTNSRzhRR1RWN2M?oc=5) - **Nvidia GPUs to Google TPUs: Breaking down all the AI chips - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxQUU9vT2lsNmEyRTdfdnBFSkVJWFlzVnlFbmY4MEdTZ2VtR3RweU5KakQzczkwOENWWlZfaVp1NEdENzFSSXJuRU1Fa0drcmVJa3JBVms3SU1iZzNDeEFrLWROTEFVUnQyTFk4blNvVlBxbzJVM0dodnl4WTRaUGhFYXdfaUJlM1JDeWhOSi1GQ2VHaUdQVmllYkR2cElkZF84cFFKc25pVlNLUQ?oc=5) - **AI Chip Startup Cerebras Refiles for IPO, Testing Nvidia’s Pricing Power - TradingKey** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxPZzlqYXlHUFl1QUJQMlhWNkJPSWtSbWpLRUIxREU5a2dTczR1cnpUMUt1bXpOQmdndlFRMWtOcmFzMzhYTTVTOUdqMjhSbThFVk5YOE82LU8zVWdtaFpENVdnTmI2amZSdlFqdlNuVzZadGtoX1dZU1lsc25nNW9jRkxnT0s5anlKeS1PbTMzNHd1bGh2V3F5TmwxNXctVW1SRXdRblREUXhaQQ?oc=5) - **NVIDIA Groq 3 LPX: Inference Accelerator for Agentic AI - NVIDIA** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiWEFVX3lxTE16ZklPT3k4WU9mQ0JTekJiZXVOUXo4YlpUTGFpdHZsMlNUN1IzbUVJcUJKUDFSTXVWczM0ZlEybjhiQ0JtRnRHa3BKaURBcC1PdXJINjZYZTQ?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Inside NVIDIA Groq 3 LPX: The Low-Latency Inference Accelerator for the NVIDIA Vera Rubin Platform** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/inside-nvidia-groq-3-lpx-the-low-latency-inference-accelerator-for-the-nvidia-vera-rubin-platform/) - **AI Chip Dark Horse Challenges Nvidia. Cerebras Refiles IPO Application Could Affect Nvidia’s Pricing Power? - TradingKey** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxPZzlqYXlHUFl1QUJQMlhWNkJPSWtSbWpLRUIxREU5a2dTczR1cnpUMUt1bXpOQmdndlFRMWtOcmFzMzhYTTVTOUdqMjhSbThFVk5YOE82LU8zVWdtaFpENVdnTmI2amZSdlFqdlNuVzZadGtoX1dZU1lsc25nNW9jRkxnT0s5anlKeS1PbTMzNHd1bGh2V3F5TmwxNXctVW1SRXdRblREUXhaQQ?oc=5) - **Google and Pentagon in talks to run custom AI chips inside classified environments — Google pushes for tight controls for TPUs surrounding use for mass surveillance and autonomous weapons** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/google-and-pentagon-in-talks-to-run-tpus-inside-classified-environments) - **Accelerating Data Processing with NVIDIA Multi-Instance GPU and Locality Domains** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/accelerating-data-processing-with-nvidia-multi-instance-gpu-and-numa-node-localization/) - **Cerebras Eyes IPO at 3x Valuation as AI Chip Wars Heat Up - The Tech Buzz** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxQM0tIVFhiMGl0b1gwVF9SVkFjaEF4ZmJNRXpTM1k5aDRhQW10WEliSjVNREs4Y3dUSktGVGU1TFZaOE5zOTVsME9VcE5XekpRX2VmOFdZaGkxcWdLUFc3dmVHOTZXTlVNOHFKS01WdlNDbGFUVDR2RDZYOGlyMkthM2Q3SlFLX1hENDJDc0d0MVoxWTg2?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Supermicro Advances Enterprises' Adoption of Accelerated Computing Across AI Factory, Data Center, and Edge with Expanded Portfolio Featuring NVIDIA RTX PRO Blackwell Server Edition GPUs - Yahoo Finance** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMinwFBVV95cUxPYjRjTGJ3SjJGWHlNRDFFUUtyeG1aVFN3Wm41azBGS0ZORWU1LXdsQUZtYXRLbEhqUnVlenpTNHk1Qnk1ZW8xOHVVSEZUVUpOMnlYZXUzbkdsNW5xT2dNLVhJUGtnbTdIbUtuVXNCSnlPNktjSE1sTHkxWGRSbTg4Y2NPRFkxb1V0UTdLUk1IemtnMzM4VExVTzlwRmtSTzQ?oc=5) - **This Light-Powered AI Chip Is 100x Faster Than a Top Nvidia GPU - singularityhub.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMipAFBVV95cUxQTm9hQlN3ZGVJemZ1RVBQNUNtM3RJdUQ0cFJ6LU1xNDYxLTBXdnVCM1VvMUViMGlyTlNmcDVnd3kzakRNZV8yWXhpcFhVZzJqRWhveG5yR0RSdmh6TGRGRU54MTBwQnh1LUpkUzcyLXQ0NUhXeWVSZEc2dGxoUDhJZmNUa0FRQS1JNW1FcTFfUjFaZThsM1BUZjc5eEFaelM4UGhQWg?oc=5) - **Intel’s Advanced Packaging Is Getting the Attention It Needs From AI Customers, With EMIB Gaining Ground Against TSMC’s CoWoS** (wccftech) - [Read more](https://wccftech.com/intels-advanced-packaging-is-getting-the-attention-it-needs-from-ai-customers/) - **Accelerating Data Processing with NVIDIA Multi-Instance GPU and NUMA Node Localization** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/accelerating-data-processing-with-nvidia-multi-instance-gpu-and-numa-node-localization/) - **Intel Foundry Advanced Chip Packaging Operations For AI Chiplet Manufacturing Growth - Technetbook** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMihgFBVV95cUxNa0c3aE4tR2pYY1ZKU3FncGViSmJydXFrYkdUanVhekV0cGFtVEVOZDk4V0EwajJ2YW5iTmRDcnBEeF9VdnJXLV90SF9JazBjbldGdkhZQXA0T3gxa3pQVHU1cXhMUW5MNXJmTTJuVzhoN1ExTEFfQmlUSlFSX3JLVXUwUUNHUQ?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia launches Groq 3 AI chip and CPU server aimed at Intel during GTC 2026 - finance.yahoo.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMivwFBVV95cUxOcUZJSWMwR2VRS2JPYWo2c3kyS2J3V1l6OFN1NkJvbGhaWG1GekJWbk5nUV9YbGdLZ0dxMFZjT0pRd3FPQllmOUVjbnJmMkVhemQxTzhpdEQwY2JKX05wYzQwLWlGM0F1SGVuWEVWd1R3VFlobXdnOW4xRzdoVGJBTUdONlVJX0pocnJ3VlJyZnhXSWlfNV9pSlphUG81OVJ4dXpjNW15ZlhxLWFpVFA2NURYcDF4clJUa1c4ck5FWQ?oc=5) - **Inside the NVIDIA Vera Rubin Platform: Six New Chips, One AI Supercomputer** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/inside-the-nvidia-rubin-platform-six-new-chips-one-ai-supercomputer/) - **Vera Rubin – Extreme Co-Design: An Evolution from Grace Blackwell Oberon** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/vera-rubin-extreme-co-design-an-evolution) - **TSMC to boost capital spending as demand for AI chips surges - Financial Times** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMihAFBVV95cUxOMlhESm14cGR5dlJzTGVwck9YWEtEUVFjVWdOMzluOFlPekxOS3dHZ01vdUpWVFhXQklrRXlpUENVMnRjNkZIRVJ4YzZXZGJRRFNnTC0wNVJMRFRkVEdEUGlJZDJFOTRmUDFwaUk4VVdQcWZ1T01xb0pSVjg2RUU1TVZ0QmY?oc=5) - **This Light-Powered AI Chip Is 100x Faster Than a Top Nvidia GPU - SingularityHub** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMipAFBVV95cUxQTm9hQlN3ZGVJemZ1RVBQNUNtM3RJdUQ0cFJ6LU1xNDYxLTBXdnVCM1VvMUViMGlyTlNmcDVnd3kzakRNZV8yWXhpcFhVZzJqRWhveG5yR0RSdmh6TGRGRU54MTBwQnh1LUpkUzcyLXQ0NUhXeWVSZEc2dGxoUDhJZmNUa0FRQS1JNW1FcTFfUjFaZThsM1BUZjc5eEFaelM4UGhQWg?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia and Meta expand GPU team up with millions of additional AI chips - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiuAFBVV95cUxNaEc1R3NCLTZRdDgwVWd6UDR5ZXB5SXd4Q0c2dlBUbVpnT1ZzRU8xMnh5bWNEa1BuS25zRHg3Qk45OW1QaVk3MlE1MEhta25icVhvYkw5UXd0MjU2U2gtVmljdFBrMzM1X1FKQzRPNG9uVllMb0lRSXFvQWx3TWFmaDAyaTNIMFhabl9maFdRek1jcVpBOEJaeFMzbUgxbF82dXRKTjVCZzRqZm9iNkUwbjNyQmZ6WkYw?oc=5) - **Nvidia halts H200 production as China backs Huawei AI chips - Asia Times** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxNSG1weGxYZG5URDRRMVE1UEVraDJfOEJCWXc0cGQ3QnhTaGwwV1hBSjhSUGs2VUtEMnJFOThfVEZZaGRVa013ZldTVDZPWURkbmlsMTNhZkxRUmNROGZFQm1WNmdlUW9Ba1hoM3NKRUJNMmtoMmNNWGhUYUtQdk56VWotZFpCZDA5S252c1FwNkstNE0y?oc=5) - **US Considers Requiring Permits for Nvidia, AMD Global AI Chip Sales - Bloomberg.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMisgFBVV95cUxPUnJ0TG94MWlQU1RNTFNObUQzMkN3ekFVMkExRUhidlNyZ2xBNmZxc2VwZHF3aG5MR1lyWTlJQ09MbzRMQUNNcjdJTm5UUURYMUJhN1RJRDc3aTU5a0RRcDZBcTJVaF95c2lHeF8xVW95TG9jWmoxT0Y0RlNjTVpDZ3p6WWpMcnRManE1QmNMWE1ZVmhTUTQwQnJONWpBRXQ5MFhKVWVXc1V1dkwyVFlQX2J3?oc=5) - **Report claims Arm chips will power 90% of AI servers based on custom processors in 2029 — x86 and RISC-V on the outside looking in** (toms_hardware) - [Read more](https://www.tomshardware.com/pc-components/cpus/report-claims-arm-chips-will-power-90-percent-of-ai-servers-based-on-custom-processors-in-2029-x86-and-risc-v-on-the-outside-looking-in) - **Nvidia gets Beijing's nod for H200 chip sales, adapts Groq chip for China, sources say - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitAFBVV95cUxPNEVlQjZrU1hSX09aM1FEZndmSzR5RVFkejlDaVpUNGd2QkJRMG1fVkNKaGFrMHRFR2doTXhPUUQxdFVZeW5felVvOGR2bDhKbjMxTXh0ZHU1aHpQdEJ6ekFmc19ldHMzWUxkUW4wNFRLNlhYZTVHTUM5NnBNVFlMU3VrUjBjWjROUzdkazI5eXBYWUc3TlIweUlQV28tdldQdm1GMnRuZEtFbFRjLTNGTHRjajM?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **NVIDIA Leads in Data Center GPU Market: Will Blackwell Keep It Ahead? - Yahoo Finance** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTE45TU1qajRialRGMU1qZTlGMWVQSFlsUk1STlFiZ0o5ZnBiT1hMdWZwZGNhR190RWxBREx2bXZGUXNONVMwQUxlMTZuaHZtZUZLT3lkYlhhMGN2U2V3ZzJnTGhuaGR1Xzd6MWJtSTRyU2p1a1QwYVZMb1FDWEszZVE?oc=5) - **America’s AI chip rules keep changing — and the rest of the world is paying the price** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/americas-ai-chip-rules-keep-changing-and-the-rest-of-the-world-is-paying-the-price) - **US Considers Requiring Permits for Nvidia, AMD Global AI Chip Sales - bloomberg.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMisgFBVV95cUxPUnJ0TG94MWlQU1RNTFNObUQzMkN3ekFVMkExRUhidlNyZ2xBNmZxc2VwZHF3aG5MR1lyWTlJQ09MbzRMQUNNcjdJTm5UUURYMUJhN1RJRDc3aTU5a0RRcDZBcTJVaF95c2lHeF8xVW95TG9jWmoxT0Y0RlNjTVpDZ3p6WWpMcnRManE1QmNMWE1ZVmhTUTQwQnJONWpBRXQ5MFhKVWVXc1V1dkwyVFlQX2J3?oc=5) - **TSMC’s US Expansion Plans Grow More Aggressive With Twelve Planned Arizona Fabs, as Sole Reliance on Taiwan Appears to Be a ‘Dead End’** (wccftech) - [Read more](https://wccftech.com/tsmc-us-expansion-plans-grow-more-aggressive-with-twelve-planned-arizona-fabs/) - **Intel shows off leading-edge tech with massive AI processor test vehicle — huge chip features four logic tiles, 12 HBM4 stacks, and 8X reticle size - Tom's Hardware** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiqAJBVV95cUxQQVJId1ppRnBjbG50cl80TDBaU2hLVEpFUGVVbXUyeDhHZi1CbzU2SWZKZlBoekVCdmZUWkhkeVEtMUpoWlZ3eWZnZGFkN3FCMVRnRFY0ZGNVTzIxeXh0dkpQR3l5SmFxREhRTmpGcHZESDdOendnQXJPV3ltZjA2ODZUcS0wMXNNdERYZ0plM08wNkl1dXg0VEU4YTFkd3dxZDB3WW02YXE3NVV2bzF4QnFHY1E4OFAzQy1GelRrdHprWndwYm5NQ21MM29TQzhQeXhtcWk4RUtkZktLWmV0cGFSLXN4VUZnbFF1bTcwWFdhMmsxOGhTbm1Fdk9xa1p3NVhsUE5MZmFDVnJvOWliS2d0ZkUyTElfeDNrWjE4M0Z4S1RaazRfdg?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia says its GPUs are a 'generation ahead' of Google's AI chips - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiogFBVV95cUxOVG8zU3NmR0xkeDlaMmhNQThNZnN6MFZtV2VfbnNMT0ZYcVJFLUJiaENlTlRGNE9KMXZSdDhMZVdyT24wcE9JdWxJTWNVSFJpOEU1Vm03aXZwT2ZONnh5S1ZBeXFOOERIWVBBNlg5WnBPTVBfM2VSX29maU5UN2h2amlRVFIwN3BXdnNrVDItWHZaSDlLX2w2UF9TQzVUYVd5QUHSAacBQVVfeXFMTm9EMGExa2dMN1pKMWQ2MjZUc1hST2ZCNnFsYTFENlItc3plcm9rdjd1Y3RjLXFQZ2t2V0ZKWW1tLUNwRTRUZW1LbkpkR05JcnNteFk2MUNfcWFWZmJnQWp1RnVISzJMS3UwUk1SQTF0cU5welZqVVdvTElyS3dvS0tpVUlYOXNUOXRuREFnNG4xbzNORXRLaEtpSW1qSWtJLUx6bVJzeUE?oc=5) - **Meta rolls out in-house AI chips weeks after massive Nvidia, AMD deals - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMidEFVX3lxTE9YMXd4N2x1NTJ6NHVNYVBrMGU2M3pMUTR0OWxSTGpMcVBhWkh4WmZWRHFycVlXYUtYeDhMNHRDZXFzMGFlQVJ2ODFwY1BFVUQ3TUlxTVpMZUV1N3E5N3NnZWk5cEpBTnNVX200cTNBdm1sOHk50gF6QVVfeXFMTXFaeTZVb05qUGtpX2oxTmlUdWRVUTFlei04RXFSWXJ1aFpXUjY5bGg4azF6eUZaSUNMS29kcXZZWDZxVDFNc3FWdmZ0bENhRDZ4SV9nbzVfNUE3TUcta19lRDNYUGp3RE00MFIzSW1QX0E0cnlHbzBFR0E?oc=5) - **Fujitsu plans dedicated 1.4nm AI chip manufactured entirely in Japan by Rapidus — AI chip to be designed and manufactured domestically** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/fujitsu-plans-dedicated-1-4nm-ai-chip-manufactured-entirely-in-japan-by-rapidus) - **The ascension of Arm: hyperscalers rewire AI server CPUs for the post-x86 era - digitimes** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMikAFBVV95cUxOTFBFMGpFa3VhdHVzUmhISzhVMGlqXzhjR0tHeGR6Y3JTVXRBMVZLRFo3RjFPVk5xYmtyV1IyaDRqUV82UDRPUzBmQ3k5UVpsVFlrZm92eDlIWC00WWpYNi1Ba2poLW0wYlFUUUVDZk9BemY5S0N3S2dWci15VFhQS1dhdno1UGUtOGhQa1RjUUQ?oc=5) - **$850M in total funding: How South Korean chipmaker Rebellions is positioning against NVIDIA in AI inference - Silicon Canals** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMi0wFBVV95cUxQQ0FfY1RRRXpGZVJpeVRJM2ZpcFh6SkRhODVqM2FRM1NjczU5QXFyWURlYzFvT21yS0lvWEtOZjRhTWZuM3A3WEFWNmEyWTZLNGplb1BOYlYtVUtSUDc3YmhYZmZjaDNkYmFtZEJKM2tfSWtaeU9EUEhoVHNyRjRFSm5xMGlBSC1hd2pLQ1REd0dmUlF3dGN6dmVHVlF5Z0VVWno3cjhyRi12RmVtYmxNTDRHUDhjOTZmblBmbkZxUzkzN05uY3loNFdnbXhvVW4xVllz?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Broadcom and TSMC Emerge as ‘Big Winners’ in Custom AI Chip Boom - 24/7 Wall St.** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxORVQ4aElvSEVkc3Q5QUNjVmkwSUVZcXg2RWNPdVpEZjBISWZxTUxubjdZam43bmNnb1NFbzd4Wlo4RGxVbkp3SG1tQjdneTRWdjBRWjlaUnFWbmxaaVVtT29ZM2dXbERFTUdnc3dXUmRZNzBWMlBYN0dBb0ZQbzNoTldwemQwNTZQRVVteWNMdDVRbnotS3NqREZlenpOQ0ZQY2RIQXFQR0E0dw?oc=5) - **US semiconductor reshoring efforts collide with the AI chip boom - Sourceability** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxNdXFUOW5WUXNPN0pXYXcwYjc1LVItMlREbGdieThvZmFYamlkZ1VuT1RuOFhfYUJsS0pyalRFanRsNmdjbEViS0N5eTlyY1VSdHVwOWRYejFkZ0toWFlYbmpldmJSV3JqZGhTclFfdVFHNDVDV0t3M2ZaMmZ5MTJadno1N2JnaUFRZXdZVzBlWU5yRkh1?oc=5) - **Dissecting Nvidia Blackwell - Tensor Cores, PTX Instructions, SASS, Floorsweep, Yield** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/dissecting-nvidia-blackwell-tensor) - **Chip Industry Technical Paper Roundup: Mar. 31** (semiengineering) - [Read more](https://semiengineering.com/chip-industry-technical-paper-roundup-mar-31/) - **China blocks Nvidia H200 AI chips that US government cleared for export – report - The Guardian** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiyAFBVV95cUxOQU5xSExrUTRFajQtWU4wMUxHVkZQd2prZ0VraGxCb0hEa2pRRnhaWjNHSFQ4UHlOZGcwczJFcGZCbkgwd2VncXozRmJzWXpNRHBITnJnNGplQ01HSjNmdEdmQzFyVW9qQXpPRWl5TUJCa3k3QldZa2hOa3UyY2tSRE9MWnlzSWVqZTY1d0RQMHY3TVlMR2xyMkJBLUk4WUpTb1AtMWo4cnFVcVdXQ1Z1VFRodkRaYlJnY3dHZUFtMWpuYW5NdDBLVg?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **NVIDIA's AI Dominance: Blackwell Chip Momentum Drives Data Center Growth for North American Investor - AD HOC NEWS** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiygFBVV95cUxQb2NsTzlLSEtqSzNFbDVoM0FYanlGdkZYYU5zZnk3U0FfLTF0eXFaQjBxYXpJbkFqOFZFSE9ob1psQlVMWHFQM2h2Y1YwdktPeWtDVDd2ZFl5SFJvaG5leTFEb09pNjI3RGRKZWxzSUdHRjFoQkVQaXVubWx2UXlmSzVmQlFRZkhGWjgyNV9pNUdkZTdMb0xjUkVoLTNiWWFpVDhpbVpCSENJT2hLSDlYb3RtVE9TZktlQ0Y4LTIwY1lFRldZZFFnUlBR?oc=5) - **South Korean AI chip startup Rebellions eyes new shores for rack-scale invasion** (the_register) - [Read more](https://go.theregister.com/feed/www.theregister.com/2026/03/30/rebellions_ai_rackscale/) - **NVIDIA's Blackwell and Rubin AI Chips: $1 Trillion Revenue Potential Driving Market Leadership into - AD HOC NEWS** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiwwFBVV95cUxQZjl3Wm1zdTRfeU1lQzBmanNZbUc1b0dNMGJPVC1DLWpDenpER2MzSWdadG9FTktCWDUwOHh4NmJmQ3dOZFpKOWo5RldsUkpiZVJEWnN5dEs1RDlFUUtFTWIxNUtJVkVrN0dNcTR0aHhjbEE1bGVaczFuZ09DSnlBcUZMTmt3dmVCOUZQX0s0QWIzVDNURHM5RkdFSjlJTE1jT2RwN1I1dHI2bmpMNFo4aE5CM0ltc09VZzFnRHpUb2c3a3M?oc=5) - **US Indicts Three In Second Nvidia AI Chip Smuggling Case Linked To Supermicro Servers - crn.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiwgFBVV95cUxNNFRxQlM4ZEZpbzdyZzRWS3R6djhfVjBMQTdpWFFBZks0QU5xRnFpNS1xc1c2cjJQdV9DbTdVZ3hIUGU5bEZrTHVOcjhqS19obEZfbkE1R2NZY1ppbE5ka194d3V3QkNWaU9HQXNUZHlfSlVRT1NySUZZYWE0UkdfOVY3YktFTWYyV3VKcHFVc0UxZ2pWUEQ3YlB5Rl80bmtpRGFkSnJLUGE4SVVFWlVaaTBZbndPMU1mSWxXYXYyM29pUQ?oc=5) - **How China's AI chips stack up against Nvidia's H200 - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMipwFBVV95cUxOVzYybktZbWExUXk3M1ZaUnVUTDVJQ0hnRUc4SWNSaGlFUVE0aHhueEZLSU9ET1NiX0R3WmVnaXRwVnJsZV95OG5iSTdZV1dLRGRnQjYxOEFocUVYLUdudzE3UUhsdFdfR1JvSHRSZHk1QXBYLWtrSTNIb0dpcmw2TlJVVEVqcXU5Zi1uRU51Y3BqU0tLZy1pSEJkb1d4T09mcG1iMTdGUQ?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **OpenAI and Oracle to deploy 450,000 GB200 GPUs at Stargate data center in Abilene, Texas - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMivgFBVV95cUxOdGw2dERHOWpPTVllWTRJbkhxOExCNEtyOHBUQldBMXhzQ2ljN0NqTlJNM2pfQkhLMUN5czR1V3dXZ3BVbVRScVJZd3RSWWd6cjBqNk1WRnluR0w3alFLRXF3U2FHblRrYWNJeGhVczNyLXNodUw4VGFVQll4Wnh2X2pNYy1UY2tDcURIMWdCVUxQX0dVSjNLRHJybHViR1JWYV9IT041R3VXLWZLdG5VTGdGMUtHSGxLMXRmMW53?oc=5) - **Nvidia Brings Blackwell GPUs to Enterprise Data Centers - Data Center Knowledge** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMirgFBVV95cUxPV0NWRV9oRDl0YzB6UDJxV1ZaUjk0WmlFTFVoNExMMjJNTEFobjdqdzR1M2tobUw5QWNWNEhJdlp0QnB1alJyZUFOTks4YkF4STNUUGZxY19KZHU3RklJSjhNMHdwYjdwSmVMdTFUNmxPTGZna2Z3aFB5N2FuOURScEZZMUZJWVVBWFVQbDExT1pRcmI3MGdYMlFZVXdFU0h0R21hNzBwLU1IMXZoZXc?oc=5) - **TSMC delivers another record quarter as profit jumps 35% fueled by robust AI chip demand - CNBC** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMijwFBVV95cUxOZUJBVURjbmxmSlRIWUVKMzU0T0hiS25uMi1Ha2wxaXdSX1RnbWR3S0c4c1RVQmZ3VXBweVY3SGE5cVJ4YlRSalotb3VjcVZaZzJRZU5VWnh3NV9iQjd2LVlRRXpLZXd2a1ZYSTZoQmdsbFR6Z1BfS3lSM1hlR1R4YVYwUU4telc5UHFvQXRjTdIBlAFBVV95cUxQTTRtRHRxVEJiYm1PYXNtSmNrclN5alN4U05LT1dsN0VqM0FwbUx5S1F2NFFZdVN3ZnFiRmZLTW1sYUk5bWQ2aG53UG5BWDBENFNpMFBlV2tVSW1GaTM1Y2pKWmZGS3JYTTU2WVlYcVlqQUlzYlNsU2MyM1hiMkctQWhUdmgyZ2VPS2tDc2ExV08tbFE2?oc=5) - **Nvidia to launch AI chip for data centers in space - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMinAFBVV95cUxOVl94UVFMaFhJUmM5aWM1QlRRajRVTHU0SG9ZNG1vMU8xVk55LTRtdDFFZFlXREd3akRwYThWVVk1WFdwTmNnRzd2RWNXR3JJRUVhck1BOHk5b19jSXZnSEVsYlF2RmZhdHdReEotZ1ItWkkteDRENUI5Sy1TNTZocWJsLWlVNUFJZ1B5dnYzYkh5YmJESTR1S2U2dkw?oc=5) - **TSMC Expands AI Chip Production to Japan - 24/7 Wall St.** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMijAFBVV95cUxNaVpZVV9hS0hYTjNrMkt1MkcwZmUyWUY5aXp2Q1NjcF9UUjdKR29RdUI1a0wwX2lwTVpKX0ZKV2VNMzRZZExTaTVLaE8yOUdBbnJtZ3FmVF9CSkVTdldXQTBPUFZQaVh5OW5Db2EzbzQxc0xJd0sxRU9kVnNReDNEZTkyQU5RSnE0T21qNw?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Data Center GPU Market Size, Share | Industry Report [2034] - Fortune Business Insights** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMieEFVX3lxTE9ZOEhOLVRsLThWdkhVZ3hfaG1xV1ptekhLVFI4ajB6X0VWcWI2cllzLUFZa3FhbGlDSEtDY0kyNHpwb25uMWdUSkp3ZUN5N2VrelBORkFBTXRvYjNrWE9ZM3Q2TVNZdExZN2haTm40MnNTNFhGd0ZOUw?oc=5) - **SEMICON China opens with focus on AI chips and advanced packaging - digitimes** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMimgFBVV95cUxNaHMwemN0djVzV3F4ang2MjFKYlZ4OUh4ME1fQ0xVallfN3B6VTJSbDFwcmF5S0hyMkhrU0VvMDh3Q1VkOXlDNVUzTHVRLWR4QWtRc0taekt4bkFGSDdndWRCWUZzU0xyaDI0b3l1c2szMlpObFFTd1hrdl82cl9Td3pGdUpMREpBcmdyRFR4TGQwYm9ldncxN2dn?oc=5) - **Broadcom vs. TSMC: Which AI Chip Stock Is the Better Buy? - TradingView** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMitAFBVV95cUxQS2NSbmpiZE9rRkZMT0F5X3RrUDF4WDMwWmhjUjIwMXFTNXd4NTdXMlZYNDdHODU4U0gtMDNxeGxDVk95VkxvX2xCc2Fsbkp6MWMybmZDUGl0eEZRMzVjbVRTNTJpTTF3Qm9taEY3REhMZDM5d0gyV09NNzlXVEtpbjY1N1V0Z2FHNjRmV0l3bDdTWDQza2xub1pZTWJpMVN6TjBXM1NVVDFZMmE3WkppbTREVGY?oc=5) - **AI Chipmakers And Data Centers Fuel Wealth Boom - Evrim Ağacı** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiiAFBVV95cUxQS3FPaWh2alczOVlDRFdFbzhSVENQUHVud3lWMVRucVhJV2g0anJWTTFycy0yRU9wQWxyQmNsTEJpV2FLdzZZUkZnd2xoRWZhWWRMbUY4UEZnbEVGbHVpWnBUZlpsSlRNWGxEOG9QTGZjYXFELVozeUZ2WjlEVzJyTmRybmVrdU5T?oc=5) - **Meta strikes AI chip deal with AMD days after committing to deploy millions of Nvidia GPUs - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMipwFBVV95cUxOc2ppUVhkZU03cXN4cUNwS3RXdEJJcmJST1RBUnBIcEhOd1E0VFBNekFoVjRKelJGeWEwckZlLXVJVGY5TEpiT0dELU5aaG0tNktmbzF6bXNXclQ5Q1E4SDdWM2p1UXd6NzJ1dWF5MFhnN1RDNDVpdTFqUmhLaU5ZMEdIQ3Rnbi1lZ0FCNVhET25sblVxSlFZTjU4RzZzLWhDcXFRUFJmWdIBrAFBVV95cUxQbU1GQm44YUdzT19wdVhFS1A4N25LMnp5NmlnMS1vZEZLdktUa2pCNlRkOElYYnNPSGxTcGNKeHA3QktGc0ZNVDYxTlNEZ01GM1phYUMwWEprU2htcjltSEFJa0FLLUkzZUIzN3F6N2NnTDNqSlZBVk9xYXJfM1M5d25TOGJaM0lHcURLZllvUjFUb1M2ZC1rMUFEUjYxcV9rdTdwQWg0cUtUSEpy?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia Puts Groq LPU, Vera CPU And Bluefield-4 DPU Into New Data Center Racks - crn.com** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiyAFBVV95cUxQN1FtelBYMXpmb3pDcVpwQmRjNGVXNTgxcVZaQUxhRVpvdUxaNmJRVWRvbWlycTRVMFJyUW9pd2V1b0VJZEcyZmJBT3hvY1ZjZ2VKcnZOT1ZBSTNFZTduT25pYVJCdkM2WEtIcksxZkpLWmdrYWhoQm8wWkpCWnRuaWZYTDJPcWoyV0hxZ1UyVGJNMXp0cjVjdHp2bUZnRTRVam9xeHdYWnVucFZtU1lxVzMxNXZjU1RVWk1tQWRkUnFaWEJ0dUNvNA?oc=5) - **InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper - Formerly InferenceMAX** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/inferencex-v2-nvidia-blackwell-vs) - **NVIDIA H100 Tensor Core GPU: Powering AI Revolution Amid $500B+ Spending Surge in 2026 - AD HOC NEWS** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMixwFBVV95cUxOeUt2cTViSDZzbVRJbHRydVBQbkhhaGF0Y2U1dTB6X3FnSDFNTjVfQ0pWMVFoRnVFamZEOWhvaXk3RnpzQmFwdXVSQlRWX3hyMk1xU1Zva1g5TU5VUE5NNjh5YmFSTmN6Qzh4dzEwMGdOd0FGN2FyUmcyS1NlWVB5QW9STmtWaW9hRnM3NjluMlhQc29idkF2ek9zWXRheE5TTndYVDFiNkdYem1NZUxjcnM5MGZhbHowQmRtalNMV0hxTWl3OXdR?oc=5) - **Nvidia Debuts an AI Chip for Space-Based Data Centers - PCMag** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMikwFBVV95cUxOTF9LcVA4dlU4NFVLejV5UDhwU05iZzlZTGdXMEtZdzVueUFCNzkzcFFhZzVQWmFlbHhRZllUZ1ZMNklaRFF2ZUx6U0ttY0hRcklYLXloaG1rd1Q0dFI2RHphQ1lmTmdFQTZoanY3MngzNFJUNU9NeVUxUHFYWmZfX1VVam82S2c0R2pydmpSNlVCYkU?oc=5) - **Huawei’s Ascend 950PR AI Chip Just Won Over Chinese Customers By Mimicking CUDA Through CANN Next, Threatening NVIDIA’s Moat** (wccftech) - [Read more](https://wccftech.com/huawei-ascend-950pr-just-won-over-chinese-customers-by-mimicking-cuda/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **New Nvidia AI chip design raises questions over HBM demand - The Korea Herald** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiV0FVX3lxTFBnT083VzFyaEE0UTFGeDJKckVQLTFwalpWLTBkNmVwVEFWZkd1YjBLS2RmaGk2MjNrR1I0YmRRa0xhT0hCMmw4Nm5QbkY4WlY4NHA2YTBrWQ?oc=5) - **TSMC Has a Monopoly on Making AI Chips. Here's Why This Stock Could Be the Safest Bet in the $700 Billion Capex Boom. - The Motley Fool** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMimAFBVV95cUxOZl9DOFZOWW1mSE1wSklRTko0NDNVczg5bkZ6VTJwU0dqMVpJVjRyOFh2WDgxQXVMM0JEZXpRUTV6TXhESE44dkQzS0ZOMERqWTdOQTFvQmRITDdwM2w0bUNhV2I0MnZ5N0IyYVNPVGhpMWRYY0FnOXJRbEs0WWZ4b1NFTjNWSk5fUndVTU8tN20tTkJmeW1DVA?oc=5) - **Musk’s Terafab Plan Puts TSMC’s AI Chip Role In Focus - simplywall.st** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMi4AFBVV95cUxQZ3ZzX0lFajNFMkxSemJNLWFBd0YzLXU4RWFqNW5vcDNqcFhoekZiamEwVVVESVFiNllKQi1wSkFmd1NoOHVjQTZjWF84c0Q2YklZeEN0LVlGX25LXzZkRTJ4MWdTcnYxblNWRmNfTDhoSy11UmM0Zk1yU3Ztb19vOEJRdWd1WXpNdlN2SERPaHJMejVyelFNTEdkM3R2NGlFalRBZFVSWWxaUHNmNW1rSUhJWm9HbDI0Sk9KUTVTVlJPQnVWSUVzcTBDbDNBYjIwS0R5UVowWUhMRjdZclVqeNIB5gFBVV95cUxQRVhoY3JZS2wwNGJibDNPaHZ4dUtIRXRVcjBqRXBfZEFBRlp5aGU1SGtoTnJmUkpFdi1INkEtUmVpWFlGcU5HNl9wYzAwekRqd09Hd1I4N25NbW54ZDZoZjl5Z1hKRUJmekJCa1p6Z0kxSmFYUnFhelFOdDNjT2E2S1NudGc0V01GN2xRazdubTY4OGZpYjV3MGdBNlZoRzRvWlRUQWtUNGVCUGllU09WMDVLVlVqb19MZ0c4QWw1OU1xMXhNc2ZPMkFVLUxCRzNuQ3I3YmtUY25CQ09YWEFrWHBOVjR1dw?oc=5) - **Nvidia's H100 GPUs are going to space — Crusoe and Starcloud pioneer space-based solar-powered AI compute cloud data centers - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiigJBVV95cUxQZllrWXhKMTBZWl9GaHJSeVZrMm9Wek00NU83dkxRTjcxazd3eW9YRnlSb0dNSWxxSmd6TWpGU2l5RnMxY3J1a3RSbEZVNDJTdFB2ZTVHUkdHTjhPUFJZZ3RZVmE0cmdnM0J5cXNoc0VoOExVcUVrZW52TW1lX1U0RVJocFFNS3hoVzVCZk9PQ2FGY3pDZVNqYUxLQmlqU3lqYzlKQjhvT09NUWVfNG52UWNGMEVhYTQtSkhuMVZ3Y3JPbXVHYUtaRVZMeS0wMVhGeFdzRS1KbGFqdDJ4U0tIMnozZEpBLW9MY0ptNEQxcGpDWGFYd2EtV2FQaUlGT1ZoTmRrYTZ3RmhRQQ?oc=5) - **Meta expands Nvidia deal to use millions of AI chips in data center build-out, including standalone CPUs - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTFBiLXZYX1ZjaTRaenZCcmpJT0FZTksxVFpNOWhYOXBHenZDUjlKLXBoTDJuOHluYzRiSWx0YVV6Slljb3NBem9CLVlJUHlTR1FIQk15ODZGRm4yaXduckZ6YW9DNTJoYkZveDFwS3Y1amFOTkRiSi1lNDYxZlQwMFXSAYQBQVVfeXFMTVBJeVBlbFhKZDhpWE56QTZ4VDFJYjlrSk50eFgtQzViYUduMHRZRmJ2amNRdjZDeVFmUnpfNE54LUhqR2ZTSWR0eXBDcE13Q2wxekszejRCTFlKSHRZWDlWZDgzb0pqZjE4QTdrd0FhZDhQSTNHWDZDMlQtNUYya1RTVkJO?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Intel sets sights on data center GPUs amid AI-driven infrastructure shifts - Network World** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiwgFBVV95cUxPZDAtWno4TzVVSjNsRlRveldub3ZxWE9MWDZtR3QtSmNQQW1wWGxYbDJvWHBSdEFKMTY2aWRHVmlEMjUwbGpKMVdicFJuWnFhajJJZ2EyZ0dkMDRBVkdwWHBuMVRuZVVzNGpKSzVDdUpFNlBUc0NLZXdKN19JTDJKY2dyWTZSUHZzWmdyYmc0ZjJhbXNlMU0zSmxQNV9UUGhReWhjRnZFOHNlVGRWYTNZSndCTUJOVjdUTnlVVkJtd18xUQ?oc=5) - **The Super Micro AI accelerator smuggling scandal proves how cut-throat the global AI race has become — as global trade evolves, so does export control evasion** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/the-super-micro-ai-accelerator-smuggling-scandal-proves-how-cut-throat-the-global-ai-race-has-become-as-global-trade-evolves-so-does-export-control-evasion) - **Huawei unveils new Atlas 350 AI accelerator with 1.56 PFLOPS of FP4 compute and up to 112GB of HBM — claims 2.8x more performance than Nvidia's H20** (toms_hardware) - [Read more](https://www.tomshardware.com/pc-components/gpus/huawei-unveils-new-atlas-350-ai-accelerator-with-1-56-pflops-of-fp4-compute-and-up-to-112gb-of-hbm-claims-2-8x-more-performance-than-nvidias-h20) - **Nvidia Debuts an AI Chip for Space-Based Data Centers - PCMag Australia** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijAFBVV95cUxPYll2NDR2LTVXcDMtUUVqNjlsVko4Mk5MWGNhWlJrbUFaX2xGMXNSZVFsQkZTX3dFcWNQWVdHSjJFdWptdUFNQ0hNT3Nsd2FjT3QtRXNSOTdhdXFFR05OcFM0cGNuWXVnQ0VfTFQzaTgxVVFxSFVfU2RBWjctSVBMWlhCM1ZtdVQtOUltbw?oc=5) - **Data Center GPU Market to Reach $1,026.28 Billion by 2040 at 24.38% CAGR | NVIDIA, AMD, AWS Among Key Players - openPR.com** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMilwFBVV95cUxPM1dmRlZfQ0lTdmxsNW1OdWQ3TTdDQzJfNjBrZVlwR29aMTN6REYxQ0dlOHc2NGg0Q0tIZkpxcEJjRXpVLTJWTnF5R0tGbzRNNV96YUNkWU1QeWU5UXBuSlZtcEJ6LUFacE5LWDBzaFJpMVBCUEhWNDZkRVdUNWg5a1c0MnpmNUdRNE1RcVpKaTlMRDc3N2Zj?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Accelerate AI Inference for Edge and Robotics with NVIDIA Jetson T4000 and NVIDIA JetPack 7.1** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/accelerate-ai-inference-for-edge-and-robotics-with-nvidia-jetson-t4000-and-nvidia-jetpack-7-1/) - **Nvidia to supply more than 260,000 Blackwell AI chips to South Korea - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMivAFBVV95cUxNbW9XWUFoYkxZaVI0SEtjV2dMNWItSnctSGQ5ZGs2MG9CcTVKNnRKMGoxLTlibVJnbmp2WWFzQ01YRGlXYnBVMjdiWWp5VU90SDNMUktpMlAxRi1keDNDUXVNN24yRlV5UVlBd3ZsRDlVczgzeWF1bTU5Yko3amU2aU84LU1OZ1VzUkloQkIyZUE4eXp6RlFmeUVKYnktNmE2SnN1dzdmM0NLOVhYOFF6c2lGUV9yMUJFekFKdA?oc=5) - **Nvidia's $20 Billion Groq Acquisition Just Paid Off. This New Chip Could Change the AI Inference Game in 2026. - The Motley Fool** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMilwFBVV95cUxNeEZvYnBkcnpjSVphbFNFeHNkeVBEQnFyamZuenlwb19JZXI3cUxzV20tVHh0QXhpU2V2WFB1b3pNVVZzQ3FKRENWT1MzbHBoc0tVdmR1NzAycGtpaWRkbHZIQkxWZlZiMkRzZFIybjU4ZEdjdDFWTXduYTBSS1dMZUJLS2wyNW5uRWVQN2FHVnFQSm9BTnRJ?oc=5) - **China semiconductor expert suggests vigilance in buying Nvidia’s H200 AI chips - South China Morning Post** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMizwFBVV95cUxQV3dUMS1CLUg1SU1yQWg1X0d3RC15YU5qeGhyQmIyVjJxckNqcDBJY1BTVHdiNUtMWVN1dmxnRHd6TGZJeGg0ZFp6SENDWjRmaWdNaC1aRjZIckdDUHJrMnVhUERhd09iTVZPVkVKRV9lMUhwQU5zRUw1eWJrdS04WWN2UkQxRTZCd3VVQW95LWNKaWQ4anREWGJEeHlvRGFUR0RpWUFsemxMbTQwMmR3dzVpU3hhNk9Ic3czX1U5bXZxS05yV18yVWp5TVd5VFnSAc8BQVVfeXFMTUttR0sxLWE4THUxdEx5SG0wVzdoZnF4aVF1cVJ1OUlHTXoyUHQ3Y0ozX0pLWGhUdTBBdnlLcWpXeXFNQVlPeXgtaWdtWVVfbUpuOXo3S1pFOVZJY1hKUXNWLUVVNno4a1JPQWFGWVZ5cHY2Nm9NUXlTU2pxQUF0MW9vWTZLNXJZUjdzUGI1MkZhbTFaSUM3OENwLUE3XzhIZFVwcjdMYVdwb2NlUEI0OFFWYXp0NTZobFJHcTRWS3VWNlFUenRRalFXX2hKeHRn?oc=5) - **Trump greenlights Nvidia H200 AI chip sales to China if U.S. gets 25% cut, says Xi responded positively - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMidEFVX3lxTE5aS194WTh1V3I5MlNzUkthMTl0cDJMdzV3UkxxX3JPX2p2SlFsLXJZanNaUXZfc05OTHVJalI1aEt2TXZRR1J1RGNrWmVJYm9Jd1FGOFJveENudlNHVjFNX0p3S0kzR0UtRkRyTGZXRy1QVWVJ0gF6QVVfeXFMT1NmclpBWFFJaThZWUFJd0t5bkZ2SzBTeTRHbGhtbzVJLU5TVlJCaXBlbGJYU2xtM0lqbXRRcVlPUzlveEE4VXFTT182RFZPVXhxSExPWU8xZ2pyNzNEVnQ0cXpVXzlBQ0lnRzdLU2hralFfSllCZTJGZ2c?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **E2E Networks acquires 1,024 Nvidia B200 GPU cluster for Chennai data center - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiugFBVV95cUxOR29qZVM5SkFFdjBIUmlQcTNFejk4eHJxVklNMVo1d18yRmZpTUtHdGN1Zk95V0hEN3VieGk1LW52dHB4TzhrUzdNZFFONU9hWnYycEN6ckc1SXZLcVU5OEw4OUp3TC0zT0trZUhYSGI0X29MTkd0WllnSXR6eFpkbnd1Q081OEgxeERMLTdLeVJ2MWR4bW50MHBrNGZKbnR1QjlqOUY2RUQ1T3h5bFFhcDNEZl9LbmM1aUE?oc=5) - **New Software and Model Optimizations Supercharge NVIDIA DGX Spark** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/new-software-and-model-optimizations-supercharge-nvidia-dgx-spark/) - **Nvidia GPUs to Google TPUs: Breaking down all the AI chips - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxQUU9vT2lsNmEyRTdfdnBFSkVJWFlzVnlFbmY4MEdTZ2VtR3RweU5KakQzczkwOENWWlZfaVp1NEdENzFSSXJuRU1Fa0drcmVJa3JBVms3SU1iZzNDeEFrLWROTEFVUnQyTFk4blNvVlBxbzJVM0dodnl4WTRaUGhFYXdfaUJlM1JDeWhOSi1GQ2VHaUdQVmllYkR2cElkZF84cFFKc25pVlNLUQ?oc=5) - **Real-Time Decoding, Algorithmic GPU Decoders, and AI Inference Enhancements in NVIDIA CUDA-Q QEC** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/real-time-decoding-algorithmic-gpu-decoders-and-ai-inference-enhancements-in-nvidia-cuda-q-qec/) - **AWS Trainium3 Deep Dive | A Potential Challenger Approaching** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/aws-trainium3-deep-dive-a-potential) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Inside NVIDIA Groq 3 LPX: The Low-Latency Inference Accelerator for the NVIDIA Vera Rubin Platform** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/inside-nvidia-groq-3-lpx-the-low-latency-inference-accelerator-for-the-nvidia-vera-rubin-platform/) - **Musk's TerraFab Aims 50x AI Chip Output - 조선일보** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiiAFBVV95cUxNLWYtR2QzSGRpNk94d0lILU5WMHpEZUhvXzFCSWpMaXNGX1pvcDZtQlZNd29NQTVZM28xNmE5VmZOMWZ0MEs4NEp2eVQwZ3dPVFdoQm85ZUc5OEI1OVdGalZ4Xy1tWmw2YjlUZkNqQnpsZmpaYTVWc0tqOTBwaWFuamZaOEJxNnJw?oc=5) - **Accelerating Data Processing with NVIDIA Multi-Instance GPU and NUMA Node Localization** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/accelerating-data-processing-with-nvidia-multi-instance-gpu-and-numa-node-localization/) - **Supermicro Advances Enterprises' Adoption of Accelerated Computing Across AI Factory, Data Center, and Edge with Expanded Portfolio Featuring NVIDIA RTX PRO Blackwell Server Edition GPUs - Yahoo Finance** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMinwFBVV95cUxQY1pyeE5venJvZUp4anBxZXhXNy11c0JKdWpBbFl2T1lteXZvaW8tbG5hRnVlQmZuOUN3QmJEWmdRRjlBWFdISmpMajVVM09jWnVVVXdZSWRRZncwek9IdWN0d3V2Mnd2VUttbHAtenZEc25WODk3TTB1a2laQU9yRlJIdXBKQm41ZF81bndDSG5EdEVHTkJSclJDUG5PNGc?oc=5) - **Scaling NVFP4 Inference for FLUX.2 on NVIDIA Blackwell Data Center GPUs** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/scaling-nvfp4-inference-for-flux-2-on-nvidia-blackwell-data-center-gpus/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Supermicro Advances Enterprises' Adoption of Accelerated Computing Across AI Factory, Data Center, and Edge with Expanded Portfolio Featuring NVIDIA RTX PRO Blackwell Server Edition GPUs - PR Newswire** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMi2wJBVV95cUxObEx3MWhFd3lmUHZFNzlnRnlJbjEyN1ZzdjZGMGZJOTBTd3ZHUENBb0xGVFZ2WlUtS1phMFRZSWNpUld1RU1UdVdQMFJ0V3pWcXkzWU0wc3dnWjRMZThfUVdJdThzR3pmc25RSmp6U1lkeXVzSTMybVR2Q2dQRTJyUnh3V1B4ZmtMbHFOZ3N2MVo4aGhJTURKTWdxM29vTFZGWmZON2RyeGp3RnZ3RF9SVEJTZFk5YkJKZkVUMFN3cWNKeFpERGppT3ZpUjRWb0Q0Q3QwaVRXMjk4Rm92TVpPb1RUOUUyMWFfb2pqXzVKNFh1Tm9jY2ZqNEZDWUo4WGsweFlGaVR5M0RpNnh4ZDRjWmFIUWdsLVVXT3NoWlFFeUQyallHa0N3YVBJZGRtdHpyZ0JxYzZPWDI4eTdvSzM2cE9PTDE4WFhPZnZoMVEtQzVzWWVZV0piN3RmOA?oc=5) - **How Nvidia's $20 billion Groq 3 LPU deal reshapes the Nvidia Vera Rubin Platform — Samsung 4nm process serves as bedrock for SRAM-based AI accelerator chip** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/semiconductors/nvidias-20-billion-groq-deal-produces-its-first-chip) - **Nvidia updates data center roadmap with Rosa CPU and stacked Feynman GPUs — optical NVLink, Groq LPUs with NVFP4, and NVLink also on deck - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMijgJBVV95cUxPdVRraWh1ZllwQ2pyR1J3Mml0VExDbzNET3BRYW1SR0I2YmNOQ0c0blZLS252Sm1hXzZBNFZCdllQVEd4LWRDSVJoM0RTdHgyYUprdTM3dkJfbHZYV0tJekRlaFZ5M04xQjhORVdTbFVpa2hTNXVablZyak5LT01yMnN1dXJVZmhOeE9uNFZCeFdqZTdhT2hCOGdsRmlOeFNZekVVcUYyd0VOSUZFaGRMMmhfTllfb0c0akduWmoxNkFPRzdNUHREa1NGY19KbWQ1clh1VXJpM0pfSkRKMXRnVTJrdHZnMEdGeUc0T2E1SWlZc3Y1WmVRbkJzZ0tYam0xdG9MQk5RRzNUMEx2dEE?oc=5) - **Analysis: Is Nvidia's Groq deal the endgame for AI chip startups? - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMihgFBVV95cUxOd2phVjFhTEtBaVJPSXFxV0FDbC1PMXBjZGpGRXlUTXdfRjRFOUdBUjhYUnc3bG1WZzFQb2xPeGdSTm9KUWlVT210WGgyTlVqRmk2VGRJVGstVUFkdjdienZDSmMxc1ZBY0IwaFRYSVkyQzJEMFpZUHI5cXp6X3JneFhxRFVaQQ?oc=5) - **Nvidia unveils AI chips built for orbital data centers and space missions - BetaNews** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMijgFBVV95cUxONDg4Wnc1RWdmQlpIX0VzYVJpR0liY3duTFRQR004ek53VWJVY1VjWi1xcTNnSXIwSTVXZjN5TFpidTB1aXhPa2QySkpOS2JneTE4dm12UHZHZTVKR2xxUVhEN0k3YWtLdm5XdXFITkh0SUM3ZjVNMDUwVml2YXVIcnZkZVpFNU11bkRKN0Fn?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **AMD and Samsung ink memory supply memorandum for EPYC and Instinct products — unprecedented deal also includes scope for foundry partnership** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/semiconductors/amd-and-samsung-ink-memory-supply-memorandum-for-epyc-and-instinct-products-unprecedented-deal-also-includes-scope-for-foundry-partnership) - **NVIDIA’s Vera CPU in Detail: High Perf Chip Takes Aim at Broader AI Server Market** (servethehome) - [Read more](https://www.servethehome.com/nvidias-vera-cpu-in-detail-high-perf-chip-takes-aim-at-broader-ai-server-market/) - **Decoding the Future of Inference At NVIDIA: Groq LPUs Join Vera Rubin Platform For Low-Latency Inference** (servethehome) - [Read more](https://www.servethehome.com/decoding-the-future-of-inference-at-nvidia-groq-lpus-join-vera-rubin-platform-for-low-latency-inference/) - **Vera Rubin – Extreme Co-Design: An Evolution from Grace Blackwell Oberon** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/vera-rubin-extreme-co-design-an-evolution) - **Inside the NVIDIA Vera Rubin Platform: Six New Chips, One AI Supercomputer** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/inside-the-nvidia-rubin-platform-six-new-chips-one-ai-supercomputer/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia disputes allegation it is preparing a custom version of Groq inferencing chip for China [Updated]** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/with-h200s-set-to-flow-into-china-groq-is-reportedly-set-to-follow-nvidia-is-allegedly-preparing-a-custom-version-of-inferencing-chip-to-penetrate-region) - **Decoding Nvidia's Groq-powered LPX and the rest of its new rack systems** (the_register) - [Read more](https://go.theregister.com/feed/www.theregister.com/2026/03/19/nvidia_lpx_deep_dive/) - **Nvidia reportedly preparing Groq AI chips for the Chinese market - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMikgFBVV95cUxQdHBUeHJUalNtUWJQRl8yRW54Q1NkaUFZMWJOYkJjNTB2d2FzaU5rYk5LZmdhLTRBSl8xak12UnVmdFFYdmllOGtmVDMwb3pvZWVFVU04QlUzMEhfbDBaOWNYcHhoOEZueW91Mm15WjJfRmJMR2dIZFR1d2FTZXZ1cENTQlhJSXRJUm1qWUhUQ0hnZw?oc=5) - **With H200s set to flow into China, Groq is reportedly set to follow — Nvidia is allegedly preparing a custom version of inferencing chip to penetrate region - Tom's Hardware** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiogJBVV95cUxPUXBGcHVrZDNTYzE3dXNHQml5MFBxSklNZDlwcFZFS3RWbTRDczJMWnduUF9RaXdHTERJVWxXc1B1Qm1VY2JtN3g2UWZ3M09HdENMbVFrajZ3REp3M1Z1YTF4YS1ZNjNpS2VTMDRFUDNIdl9WSTlTRFM4cGZVZXB2cVBtSEVBLUhmM0Z5bmFhd3NjcGU2UUFnSG83aTljQWIydTZiUVJNTXJhS29fOG9OOExjX2pEYWo1eDZKbzZ0dHgycy04M1dBVk5wUEdzbE1hTzZxa0NWejFMX0FhOGFyYlVrREl2RWxpYVRHQW5qSTJNWUtLUFdtcTBMeEktd2dWRWtYU0tCMkVralRGbEUzbk4yWXFsRUtLdGFadzFSaXBmUQ?oc=5) - **Nvidia gets Beijing's nod for H200 chip sales, adapts Groq chip for China, sources say - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitAFBVV95cUxPNEVlQjZrU1hSX09aM1FEZndmSzR5RVFkejlDaVpUNGd2QkJRMG1fVkNKaGFrMHRFR2doTXhPUUQxdFVZeW5felVvOGR2bDhKbjMxTXh0ZHU1aHpQdEJ6ekFmc19ldHMzWUxkUW4wNFRLNlhYZTVHTUM5NnBNVFlMU3VrUjBjWjROUzdkazI5eXBYWUc3TlIweUlQV28tdldQdm1GMnRuZEtFbFRjLTNGTHRjajM?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **China approves Nvidia H200 AI chip sales as licences granted to multiple firms - investingLive** (google_ai_chip) - [Read more](https://news.google.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?oc=5) - **NVIDIA Leads in Data Center GPU Market: Will Blackwell Keep It Ahead? - Yahoo Finance** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTE45TU1qajRialRGMU1qZTlGMWVQSFlsUk1STlFiZ0o5ZnBiT1hMdWZwZGNhR190RWxBREx2bXZGUXNONVMwQUxlMTZuaHZtZUZLT3lkYlhhMGN2U2V3ZzJnTGhuaGR1Xzd6MWJtSTRyU2p1a1QwYVZMb1FDWEszZVE?oc=5) - **Meta's new MTIA lineup joins hyperscalers' unified push for dedicated inferencing chips — companies diversify AI chips in effort to diversify from sole reliance on Nvidia** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/semiconductors/metas-mtia-chip-lineup-joins-hyperscaler-push-to-replace-nvidia-at-inference) - **Nvidia adopts Groq to tackle AI inference and expand global reach - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijgFBVV95cUxQU1lfSEIyYlJyZ01hdl9BZmYxMk54RUVpWlV0UTNvWktVbWRYM00tSC1NWmJReGNhd3ZvVTF0UENIZzJyVGNDR1JkdzUxanQ5RlN1WmVfMkdFcGFDUW9TVXVKYjUtVWh6Zk85bHRvRjg2OUQtS3VWMWV0c0JQRzFBVmMzR0psWTdCVnhCaXFR?oc=5) - **Nvidia 'restarting manufacturing' to meet China orders for H200 AI chip - Nikkei Asia** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMivwFBVV95cUxQUS1KTmR6T0F5ZWd5ZHdQV251c2RVYW1QNHpaRFNVeHZzZ0pfTWd6b1RGaXQ2NHRGbldKWDZMV2FiWncxcHJ3dlFTMzBNeU00WHBLQlU1a3R1bEtha203QXFyWEEyNjdyRlk1UFZNa0VKMWljbFA5ZmVVOURvemZkQ1VxSTVtai1WcFZhVGNvQnN5cEhsQk1YTzdZNVJFVXRXcGg0cXdtaWwwRXh0NW5MUXpnREI2QUw5czl1b1lXcw?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia preparing Groq AI chips it can sell to China- Reuters - Investing.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitwFBVV95cUxPdGVaQ1B1MEVHLW9CUGgtZzV0RS12aFM0MDR5dXdmdTQ3X3B5VXVISVhLZjQtOVM2eTJOWFhFN081ZzFXTFNfTjFTcENLX21IYk9WM005NzdyajF0bGRFMmlJTWtYLUNXZzctaWZRWjdqc2F4eFhpb1VEeWdOSlc3Z1gzUEVWWVN4MDJLdm5GMjA4ZUV3VDcxU044LUw3ZFF0U1YwZ0s5cXdfVjlvUXFuZmV4NEF0ZG8?oc=5) - **Nvidia launches Groq 3 AI chip and CPU server aimed at Intel during GTC 2026 - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMivwFBVV95cUxOcUZJSWMwR2VRS2JPYWo2c3kyS2J3V1l6OFN1NkJvbGhaWG1GekJWbk5nUV9YbGdLZ0dxMFZjT0pRd3FPQllmOUVjbnJmMkVhemQxTzhpdEQwY2JKX05wYzQwLWlGM0F1SGVuWEVWd1R3VFlobXdnOW4xRzdoVGJBTUdONlVJX0pocnJ3VlJyZnhXSWlfNV9pSlphUG81OVJ4dXpjNW15ZlhxLWFpVFA2NURYcDF4clJUa1c4ck5FWQ?oc=5) - **Nvidia’s Jensen Huang Thanks Samsung as It Manufactures ‘Groq 3’ AI Inference Chips - thelec.net** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiZkFVX3lxTE9aTmNaaUtWZGlheTJyQXBPdnNiNm1oVFNXVU44Y05IZDNwYW5jNWotSmZ4cERZTkZ4UHc5ZmJ4cnNxdjF5Q0xzdkZmYk9JWlFDVG5KNE9FSEJlX0t2clNUWUR4TGFqQQ?oc=5) - **Nvidia launches DGX Station with its bleeding-edge GB300 Grace Blackwell Superchip — now available to order and will begin shipping in the coming months** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/nvidia-launches-dgx-station-with-its-bleeding-edge-gb300-grace-blackwell-superchip-now-available-to-order-and-will-begin-shipping-in-the-coming-months) - **Intel, SambaNova Planning Multi-Year Collaboration for Xeon-Based AI Inference** (intel_news) - [Read more](https://newsroom.intel.com/data-center/intel-and-sambanova-planning-multi-year-collaboration-for-xeon-based-ai-inference) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Intel, SambaNova Planning Multi-Year Collaboration for Xeon-Based AI Inference** (intel_news) - [Read more](https://newsroom.intel.com/data-center/intel-and-sambanova-planning-multi-year-collaboration-for-xeon-based-ai-inference) - **Nvidia preparing Groq AI chips it can sell to China- Reuters - Investing.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitwFBVV95cUxPdGVaQ1B1MEVHLW9CUGgtZzV0RS12aFM0MDR5dXdmdTQ3X3B5VXVISVhLZjQtOVM2eTJOWFhFN081ZzFXTFNfTjFTcENLX21IYk9WM005NzdyajF0bGRFMmlJTWtYLUNXZzctaWZRWjdqc2F4eFhpb1VEeWdOSlc3Z1gzUEVWWVN4MDJLdm5GMjA4ZUV3VDcxU044LUw3ZFF0U1YwZ0s5cXdfVjlvUXFuZmV4NEF0ZG8?oc=5) - **Nvidia’s Jensen Huang Thanks Samsung as It Manufactures ‘Groq 3’ AI Inference Chips - thelec.net** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiZkFVX3lxTE9aTmNaaUtWZGlheTJyQXBPdnNiNm1oVFNXVU44Y05IZDNwYW5jNWotSmZ4cERZTkZ4UHc5ZmJ4cnNxdjF5Q0xzdkZmYk9JWlFDVG5KNE9FSEJlX0t2clNUWUR4TGFqQQ?oc=5) - **Nvidia Sees AI Chip Demand at $1T by 2027; Debuts Groq 3 Chips, NemoClaw Platform at GTC - International Business Times UK** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTE45bVpmenpuRURNZzQwQXZxT2psM3NVN3pzUnBJNzBYZWdmSHRlME9LR2J1NE9MbFp3YlRFNFFJdng4SzJWNk92RkpMX09Ec1FITGZXWDZvTUhQSFBSY1Y1NHJxV2Q0bHpSTDRZM1daU0NMTlc1RnhSOWFkWWZNREE?oc=5) - **Inside NVIDIA Groq 3 LPX: The Low-Latency Inference Accelerator for the NVIDIA Vera Rubin Platform** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/inside-nvidia-groq-3-lpx-the-low-latency-inference-accelerator-for-the-nvidia-vera-rubin-platform/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia launches Groq 3 AI chip and CPU server aimed at Intel during GTC 2026 - Yahoo Finance** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMivwFBVV95cUxOcUZJSWMwR2VRS2JPYWo2c3kyS2J3V1l6OFN1NkJvbGhaWG1GekJWbk5nUV9YbGdLZ0dxMFZjT0pRd3FPQllmOUVjbnJmMkVhemQxTzhpdEQwY2JKX05wYzQwLWlGM0F1SGVuWEVWd1R3VFlobXdnOW4xRzdoVGJBTUdONlVJX0pocnJ3VlJyZnhXSWlfNV9pSlphUG81OVJ4dXpjNW15ZlhxLWFpVFA2NURYcDF4clJUa1c4ck5FWQ?oc=5) - **Intel, SambaNova Planning Multi-Year Collaboration for Xeon-Based AI Inference** (intel_news) - [Read more](https://newsroom.intel.com/data-center/intel-and-sambanova-planning-multi-year-collaboration-for-xeon-based-ai-inference) - **Nvidia launches DGX Station with its bleeding-edge GB300 Grace Blackwell Superchip — now available to order and will begin shipping in the coming months** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/nvidia-launches-dgx-station-with-its-bleeding-edge-gb300-grace-blackwell-superchip-now-available-to-order-and-will-begin-shipping-in-the-coming-months) - **Nvidia preparing Groq AI chips it can sell to China- Reuters - Investing.com** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitwFBVV95cUxPdGVaQ1B1MEVHLW9CUGgtZzV0RS12aFM0MDR5dXdmdTQ3X3B5VXVISVhLZjQtOVM2eTJOWFhFN081ZzFXTFNfTjFTcENLX21IYk9WM005NzdyajF0bGRFMmlJTWtYLUNXZzctaWZRWjdqc2F4eFhpb1VEeWdOSlc3Z1gzUEVWWVN4MDJLdm5GMjA4ZUV3VDcxU044LUw3ZFF0U1YwZ0s5cXdfVjlvUXFuZmV4NEF0ZG8?oc=5) - **Nvidia announces Groq 3 LPU AI inference chip, plans 256-LPU rack - Data Center Dynamics** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMirAFBVV95cUxNZXE3Y1lIZjc0ck1HalVUTWZBSUFKVHZPOGhmUWVZTlNUNmF6VWlWZFJ5bmpnQS1HY0hJZFJpd2VfemxEakJidTFJV2lfNXo5S3kzaksxbXR3eVZmbmpkLW9mcGFaOExELWlVVnk5M1FGSjM0eUZ2UFZMZkl0UjByTE9iUE1oQ2djNXBlVTBlSXh4MWZHS0Nfb3hXVDlFMm5OYTNSYVdCd1pScnVV?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia's $20B Groq Bet Powers Next-Gen AI Chip Reveal - The Tech Buzz** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijgFBVV95cUxNYTZER1pleFVnZV9YOU16WTNHdW0zWXdwdjNpTV9QOEZIZFBuMjJ0R2otWFpZTlkwQUdzaUxlV1U0VWZOakd6VjljdV91bGZmaXFIRldpa0tjQXU4Yko4SXdQWWlTb1I4Smc2VVFzdk5DNmR6aXhzVEFpSE9PX1JCTDhmWGVpbHhadzJSYjJn?oc=5) - **Tesla AI chip delay pushes South Korean NPU startup DeepX back six months - digitimes** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMijwFBVV95cUxPb0FFTzM0bjRldnFQbXRienppT0tPaU80Q3B3RHBlU0xrdHlOcmlYMVhsMmVtYWtPY3BaSnZwc19KSHgzUHVGQlM4SGFFSXF6bmNnNzJkWXE3Z1Y3dG13UDhJSHY0dTJhLU5VS1htMFBVbkktdjM3dlhrRHV6LU9ab1pCS2dFYTZZU2U1SDVMbw?oc=5) - **TSMC Phoenix plant begins mass production of AI chips in partnership with Nvidia - AZ Family** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMisAFBVV95cUxPdGJCTnRwekRoQ1lPd3V1ajMzRTh3QVBtWDBQNXBuelNWVkMtUl83SzNLemxTR0hrVm1EbURnbVdaeHNkZjlvdU9zXzdCeEJMbk5ZcXdPZDU0M2FQdXlrdWptdzBKVzFpZUZlNTdfb3ktaWZqeHNncWZscUl4LWpJSm5DWGN6UTBOT0oyY0hieVRCWjFydm9nVEtqQ2FiWkpTbjc1bUxhal9LZU9wNlhCLQ?oc=5) - **OpenAI and Oracle to deploy 450,000 GB200 GPUs at Stargate data center in Abilene, Texas - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMivgFBVV95cUxOdGw2dERHOWpPTVllWTRJbkhxOExCNEtyOHBUQldBMXhzQ2ljN0NqTlJNM2pfQkhLMUN5czR1V3dXZ3BVbVRScVJZd3RSWWd6cjBqNk1WRnluR0w3alFLRXF3U2FHblRrYWNJeGhVczNyLXNodUw4VGFVQll4Wnh2X2pNYy1UY2tDcURIMWdCVUxQX0dVSjNLRHJybHViR1JWYV9IT041R3VXLWZLdG5VTGdGMUtHSGxLMXRmMW53?oc=5) - **ByteDance Gains Access To NVIDIA Blackwell-Powered AI Chips - Lowyat.NET** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMimwFBVV95cUxQZEQ5dU1QdExuQ0ZPZXh0UEFILVctb3I5OXIyNVhpS256b0VUTEFua2FVNWczaEFHNGZkaUQ5ZXhCbEpVSU5EWXFuS0hUSjVRT3FTd3ltUHNjRndjcjZFTkdDTjhNc1F4ZUo0N3BIMGZ1enZUTHcyZm1sMG1sblEyX2gtbXZBT2JyV1dkRTRvRjl2a3plZk1HN0FXTQ?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia details new software that enables location tracking for AI GPUs — opt-in remote data center GPU fleet management includes power usage and thermal monitoring - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiswJBVV95cUxPaWlTLVdXWXQ2a1BUZmRBSmh6MFg2dThkN3F0Y2Faa2M3Y0swTGt6ZlQyU012bm1iSXd5MTk0SHFkWnNEcW9icFpPSUdiM1NNTG5RZTROcnZub0k4dVV6UFFScUdhcGYxMlVHc1h4OG1CcWRmNHZNR3F2NEdZYndPNlNKZU5LRm0xV05DOTkxcEd2cWY3cHpIaFctWldDYWc5Sk1Jb3RRdlBLM1RyeE5obFhTdEU2c2p0YzloRGJLWE1Td25xX3Rjb3gwTjlZQTFHSDh0cFJEQlBpNGFTWkViSUZhVHFkak4zdjJFVkVfOXByVlNfXzJxYldMOUJKYzBNdlF4U180WjdJT2FEZXI3ejhXR2JxZGZfWFVwSlZERDVXSmJfcWp2M1h5VTBzRGlnMU5V?oc=5) - **Nvidia to supply more than 260,000 Blackwell AI chips to South Korea - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMivAFBVV95cUxNbW9XWUFoYkxZaVI0SEtjV2dMNWItSnctSGQ5ZGs2MG9CcTVKNnRKMGoxLTlibVJnbmp2WWFzQ01YRGlXYnBVMjdiWWp5VU90SDNMUktpMlAxRi1keDNDUXVNN24yRlV5UVlBd3ZsRDlVczgzeWF1bTU5Yko3amU2aU84LU1OZ1VzUkloQkIyZUE4eXp6RlFmeUVKYnktNmE2SnN1dzdmM0NLOVhYOFF6c2lGUV9yMUJFekFKdA?oc=5) - **Semco seen supplying ABF substrates for Tesla AI chips via Samsung foundry - digitimes** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMikAFBVV95cUxQZmlMSTg5OUVUT3FjVHFnVmZwXzZ2WTZwT0d6QXhZNEdOTUdjSWFzODZPa1FKX0J6X2IzSzVycGxkVG1JWVNfTFRwY1BWUFNGYlRicTZIZkZXSDBRRGVORXotekpiMHJDRlN4d0xPN053VmRGb3psN3ctRmdBY29XaXBrZVR5VFduOUJ1WGhmdUg?oc=5) - **Data Center GPU Market Size, Share | Industry Report [2034] - Fortune Business Insights** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMieEFVX3lxTE9ZOEhOLVRsLThWdkhVZ3hfaG1xV1ptekhLVFI4ajB6X0VWcWI2cllzLUFZa3FhbGlDSEtDY0kyNHpwb25uMWdUSkp3ZUN5N2VrelBORkFBTXRvYjNrWE9ZM3Q2TVNZdExZN2haTm40MnNTNFhGd0ZOUw?oc=5) - **AMD, Broadcom, and Nvidia join hyperscalers to define optical scale-up interconnect of the future for AI clusters — Meta, Microsoft, and OpenAI to benefit as speeds eventually scale to 3.2 Tb/s** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/amd-broadcom-and-nvidia-join-hyperscalers-to-define-optical-scale-up-interconnect-of-the-future-for-ai-clusters-meta-microsoft-and-openai-to-benefit-as-speeds-eventually-scale-to-3-2-tb-s) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia-Groq Deal Validates Non-GPU AI Chip Market for Low-Latency Inference - News and Statistics - IndexBox - Market Intelligence Platform** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijAFBVV95cUxOXzhtRFRUX01vUEF2NEJRbGU1dGI0ZS02NzhGVTFnd2pqdmg5VmttY2staUMxeEd6VzduUkNMWXU0akdvU0xtdHB4Ym44VFRueHhBbDhsdmVUZjhTZUUwNmtzeFZFYldhQ2ZVOHRteTVlalg4OVUwVEg0MkNvbl9LSThNVHFuQk5yZjQyWA?oc=5) - **Fallout From Nvidia-Groq Deal Validates AI Chip Startup Landscape - EE Times** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxQM1pzQnd2TWR1SDFycDZxS0VQcHREcGJaNGdob25JeVlkNnQ5WFlTWEs0WVE2aWt5a002UmwzWjY0dkJiS2NubXM1di1wTHJ3MWNDNjQ2YUVNREV3b0hMNWR1WGJCckxBcUFaZzk3R2VwZWFTY05ObGgweXlPd1RkNW1jbE50OXBRRUhqd1R2RHpVc0tD?oc=5) - **Nvidia Brings Blackwell GPUs to Enterprise Data Centers - Data Center Knowledge** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMirgFBVV95cUxPV0NWRV9oRDl0YzB6UDJxV1ZaUjk0WmlFTFVoNExMMjJNTEFobjdqdzR1M2tobUw5QWNWNEhJdlp0QnB1alJyZUFOTks4YkF4STNUUGZxY19KZHU3RklJSjhNMHdwYjdwSmVMdTFUNmxPTGZna2Z3aFB5N2FuOURScEZZMUZJWVVBWFVQbDExT1pRcmI3MGdYMlFZVXdFU0h0R21hNzBwLU1IMXZoZXc?oc=5) - **InferenceX v2: NVIDIA Blackwell Vs AMD vs Hopper - Formerly InferenceMAX** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/inferencex-v2-nvidia-blackwell-vs) - **Meta Reveals Series of Custom AI Processors for Data Center Operations - MLQ.ai** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMilgFBVV95cUxOdE9UejFhT1paN2V4a2pWMk5TVU1KT2JfWWVOeWtuTk0xRFdmdlg0dlgtRUhlOEVNM3RDLTlaaXVzZUdGbHNTTUVEenJ6M2dsQ0RTNG1rRUhCTUpQQndZWHpFVUdKSXQ0YmM0d1p3T2xSVElHWDRKMjlqeGZ1UHVyV1V0eE9UTlFOc3hfSnUyTl80NVpCaHc?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Fallout From Nvidia-Groq Deal Validates AI Chip Startup Landscape** (eetimes) - [Read more](https://www.eetimes.com/fallout-from-nvidia-groq-deal-validates-ai-chip-startup-landscape/) - **Meta expands Nvidia deal to use millions of AI chips in data center build-out, including standalone CPUs - CNBC** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMif0FVX3lxTFBiLXZYX1ZjaTRaenZCcmpJT0FZTksxVFpNOWhYOXBHenZDUjlKLXBoTDJuOHluYzRiSWx0YVV6Slljb3NBem9CLVlJUHlTR1FIQk15ODZGRm4yaXduckZ6YW9DNTJoYkZveDFwS3Y1amFOTkRiSi1lNDYxZlQwMFXSAYQBQVVfeXFMTVBJeVBlbFhKZDhpWE56QTZ4VDFJYjlrSk50eFgtQzViYUduMHRZRmJ2amNRdjZDeVFmUnpfNE54LUhqR2ZTSWR0eXBDcE13Q2wxekszejRCTFlKSHRZWDlWZDgzb0pqZjE4QTdrd0FhZDhQSTNHWDZDMlQtNUYya1RTVkJO?oc=5) - **Nvidia's H100 GPUs are going to space — Crusoe and Starcloud pioneer space-based solar-powered AI compute cloud data centers - Tom's Hardware** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiigJBVV95cUxQZllrWXhKMTBZWl9GaHJSeVZrMm9Wek00NU83dkxRTjcxazd3eW9YRnlSb0dNSWxxSmd6TWpGU2l5RnMxY3J1a3RSbEZVNDJTdFB2ZTVHUkdHTjhPUFJZZ3RZVmE0cmdnM0J5cXNoc0VoOExVcUVrZW52TW1lX1U0RVJocFFNS3hoVzVCZk9PQ2FGY3pDZVNqYUxLQmlqU3lqYzlKQjhvT09NUWVfNG52UWNGMEVhYTQtSkhuMVZ3Y3JPbXVHYUtaRVZMeS0wMVhGeFdzRS1KbGFqdDJ4U0tIMnozZEpBLW9MY0ptNEQxcGpDWGFYd2EtV2FQaUlGT1ZoTmRrYTZ3RmhRQQ?oc=5) - **Nvidia Wins Trump’s Approval to Sell H200 AI Chips in China - Bloomberg** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiswFBVV95cUxNREU5eEdSX0NfSk1hVDV5cVBSVVdwQnd1R2o1V3NtUGxwSTVtVkdjYnJISGtjUmo4b1BBeG9DOGJraDh1NXdhQ2M3UWY0LWZEVEwyaVZ4cGhkRE8ydmt1TXlSMl9XaW5EdURvZHU2d3FxX3NSbGZISndZRHdmVDVHenRaTXVoYnBYVGFfQXpwUmFTa3FrWTFoQVBZdl9uckhwSWdhLXJDSDJacFdZazI4MXdKdw?oc=5) - **Nvidia buying AI chip startup Groq's assets for about $20 billion in its largest deal on record - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqAFBVV95cUxOQU9lN25BUEthQm9ISEdZc1FaMGhEdm14SEoxaTBXZS1jMUxjc1JURG51cEZlaE0zYUpsTHJXR2o3bmVRVmpaZnZob28yX3ZqTzdhU1BXejVnc0tZWWJqRXp4WWVKQlAyMXdoV0cxMnF5VGZDblJRLTg4YTkzS242eU1XOG1uNkRwRTJBM1ZUS2Q5RkczWWNrbkkyOWg4SjRGWkdGbzhmN1jSAa4BQVVfeXFMUGFwWC1PZjlPQkZxcGZwODBIaDBWdHZwdXpidGZwNjF0SDNWTTFDQl9FMTVIZnNfalFURzFheHJFbFBqZjFYLVB2SDh0Q1o5WENWLVZUZFpvOUdibFU3c3BRZkJmbVpzZGhicFBUdUx3cUE4ZEJnTTdKYTJaNDFFU29OdF85X0FHUWotejFGYmVLY1JYNW5RcnB5ZktnTnFKUEtsb0UyaWRXSEh4YldB?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Groq AI Chips Samsung Foundry 4nm Orders Growth for NVIDIA Inference Hardware Chips - Technetbook** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMigAFBVV95cUxPWEFSUERELXZZd3VxV2Z5VDdqTWRlNEVxMHAteWtpNDFxd2FzelNYOFpSX3JSVWo1T1dBQkdZbzFDeVUyZDBPazFNcnA5dU1UTktab2JOSGIxOXpLSC1CRG1jYlY1cnVCWk5tRFpHeXNWZVhDWWlyM2JvdHJKdW5UeQ?oc=5) - **China semiconductor expert suggests vigilance in buying Nvidia’s H200 AI chips - South China Morning Post** (google_ai_chip) - [Read more](https://news.google.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?oc=5) - **Groq boosts Samsung Foundry output as Nvidia drives Korea inference push - CHOSUNBIZ - Chosunbiz** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiekFVX3lxTE1UYy1kZThOSUttSVB4cGxva0t5YjI3ZzhFNDk2eE16c1VtbFRVTXVwOF90bGFfLURtR1l0U1hrVlRwR1VNZnh4ejV6SDZ4Y3p1RVZiZGNna0xqbUpybnRuMHFVQTRTMERBdGNoNEFkQjI0VzVmMDFhd21n0gGOAUFVX3lxTE8tTERqbDlacXluWk5LODBxa2h3WGtkNllzek5iRm9JSVJ2dHRyTmhHbDRnTm5yazZGODBtck9tNzV1ZE5UTnhmS2dYX3lSbE1LQWNHWU9jMS1VZVFHaE5iek9ibkZ3dS1qR29LaWdhYXJ6OGw1TEFUNEZiaG9MODBZazlJdnd5U1ZoamduSXc?oc=5) - **Nvidia halts H200 production as China backs Huawei AI chips - Asia Times** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxNSG1weGxYZG5URDRRMVE1UEVraDJfOEJCWXc0cGQ3QnhTaGwwV1hBSjhSUGs2VUtEMnJFOThfVEZZaGRVa013ZldTVDZPWURkbmlsMTNhZkxRUmNROGZFQm1WNmdlUW9Ba1hoM3NKRUJNMmtoMmNNWGhUYUtQdk56VWotZFpCZDA5S252c1FwNkstNE0y?oc=5) - **Shortages of crucial chip packaging material threatens AI accelerator supply chains — Nittobo's Fukushima plant is tripling capacity, but it'll take years before market** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/shortages-of-crucial-chip-packaging-material-threatens-ai-accelerator-supply-chains-nittobos-fukushima-plant-is-tripling-capacity-but-itll-take-years-before-market) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Starcloud-1 satellite reaches space, with Nvidia H100 GPU now operating in orbit - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMiwAFBVV95cUxQaUtfRWVQMmFwVHhkRVByUGEtbUZuZkRJSHZOUnBXY2VsNzhNeG1PRTJRV2xlejdMQnRMZU50ZnlUNm96MThsMktlMDlSSTVPcm9MNUNOd3FzanNZQmhHR3dSTnNTYjdOMHFTOFBFMXB1OWFUVGpxQ29xQnhucFNJVk9iNUF5Y2YwSnRrLVBVV3YtT3ZMTXhOcXFvNHJlaTJfc1dFMGRqM3o5X0dNU3JNLU5qMF8xNUthYzZUS3RXSkE?oc=5) - **Accelerate AI Inference for Edge and Robotics with NVIDIA Jetson T4000 and NVIDIA JetPack 7.1** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/accelerate-ai-inference-for-edge-and-robotics-with-nvidia-jetson-t4000-and-nvidia-jetpack-7-1/) - **US semiconductor reshoring efforts collide with the AI chip boom - Sourceability** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMilAFBVV95cUxNdXFUOW5WUXNPN0pXYXcwYjc1LVItMlREbGdieThvZmFYamlkZ1VuT1RuOFhfYUJsS0pyalRFanRsNmdjbEViS0N5eTlyY1VSdHVwOWRYejFkZ0toWFlYbmpldmJSV3JqZGhTclFfdVFHNDVDV0t3M2ZaMmZ5MTJadno1N2JnaUFRZXdZVzBlWU5yRkh1?oc=5) - **Real-Time Decoding, Algorithmic GPU Decoders, and AI Inference Enhancements in NVIDIA CUDA-Q QEC** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/real-time-decoding-algorithmic-gpu-decoders-and-ai-inference-enhancements-in-nvidia-cuda-q-qec/) - **Broadcom-TSMC 3.5D AI chips give ASIC leader an early edge over Nvidia - digitimes** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMigAFBVV95cUxNa1RUcmQyZTY3S1cxcWFLNFFWZUVvdDR2QUZ5MW5QTENrdFZ0MF9GeVRHcDY5WUNUcmw0RjZQTXJnMFpvT2RPQTFKTWFnQWhiTGpzVjUyYVphU1g3VjBxYzd0czNMVF9PVGRSbDMwUXBoVnN5djlMcGY0VmtQWmVBaw?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Accelerating Data Processing with NVIDIA Multi-Instance GPU and NUMA Node Localization** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/accelerating-data-processing-with-nvidia-multi-instance-gpu-and-numa-node-localization/) - **Scaling NVFP4 Inference for FLUX.2 on NVIDIA Blackwell Data Center GPUs** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/scaling-nvfp4-inference-for-flux-2-on-nvidia-blackwell-data-center-gpus/) - **AWS Integrates AI Infrastructure with NVIDIA NVLink Fusion for Trainium4 Deployment** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/aws-integrates-ai-infrastructure-with-nvidia-nvlink-fusion-for-trainium4-deployment/) - **AWS Trainium3 Deep Dive | A Potential Challenger Approaching** (semianalysis) - [Read more](https://newsletter.semianalysis.com/p/aws-trainium3-deep-dive-a-potential) - **New Software and Model Optimizations Supercharge NVIDIA DGX Spark** (nvidia_dev) - [Read more](https://developer.nvidia.com/blog/new-software-and-model-optimizations-supercharge-nvidia-dgx-spark/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **Nvidia Suspends H200 AI Chip Production for China Market - Mexico Business News** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMinwFBVV95cUxOSDdWclY4VEtLZUprSU9SaDVuanVzOGw1OC1KM0NleWhIOGxIVTktbFpnenp6RHBvSjM1TWhoREk2NGFhbDNYZHBEb3lDWTJicmp1SlBPTUgxRHVvclFUOEdsNXQ3SVAzYkpsLU1JX3NmQ1ZQUjFHQzVVWmZ6OTJVMU11NUxvZHhQRjczZWx4dGUzbzZOT3ZCOTZELW5zbVU?oc=5) - **The U.S. Could Soon Turn NVIDIA and AMD’s AI Chips Into a Foreign Policy Tool, With Not a Single Country Being Left Out - Wccftech** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMinAFBVV95cUxQNmZiRElDMzlWTHJBZ3U0UzRQaE5ONXZnRkV4bVY0YUNGNzlBS3AtZFVlM05XVk55QzFhR2s3UDRLUlVEeTVZYmg3TG5KTTRGOEtvLTdhNHdJeEx0UzZEOHEyekhPcmF6Tm1lWXhFY3EzeVZWZzNOanh1ZGNpZ0J2bTFOX2NjU2xQWGVSc29TRTNuUDU1RkFGb3VyOTXSAaIBQVVfeXFMTUhHVVhVQ2xWNExCRGtPM3dreGdQYlR3Q2VXVm5sUE0xeFhlY1QwSW41TG4wLWh0Q1pCNHJTREwxMmlMNVJScmRiNUVzeVFaWkNuRGkxcUFCUzdoTEdqaHRMWUVuM2xheF9BV1JKQndMdnQwOXNYa3pHVkpmZ3B3RWJXZ1F6RDVISnVMZ3pJd3Jrc01xdTRLejM1WXRTMmhkVGVB?oc=5) - **Nvidia, AMD slump as US government said to consider capping AI chip sales at 75,000 per Chinese buyer - Sherwood News** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxPNy1OclV0eG9xSi1LV25GM1RRaVVMa2d3RXBYMkZVWnpyU2lKUUdhMmlLRXY2RTlpdzRyYVIwOTYwXzc5XzVtVUFnQ1V0a0x6bVRNUDhuYWRsX3dxS1h3RmZIWXhrTll3c01aN3hRNkZlYjN0eFZ2SnNxRmItZjdtWU1GWlNIWldOYTJTV0U1Nmo0LVY4eGJocXg4WkRnYzY2Wk9WbUVEQUMyQQ?oc=5) - **US considers tying Nvidia and AMD AI chip exports to foreign investment pledges - Financial Times** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMicEFVX3lxTFAycnJ6c1JDblVDQ1JTbmZ3R09hLWh4dkJDdmtmdTAtODdhUk85aWJQd2R6UHVBYXhsbGlwRnVqSWdLVDI0S0J4U0hydkNKa3o0NzB5WFBIVHhFNHVTUC0xV19JY0JacnBNZ3dXZlZKamg?oc=5) - **Intel’s EMIB Challenges TSMC’s CoWoS as America’s Answer to the AI Packaging Bottleneck** (wccftech) - [Read more](https://wccftech.com/intel-emib-challenges-tsmcs-cowos-as-america-answer-to-the-ai-packaging-bottleneck/) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **The U.S. Could Soon Turn NVIDIA and AMD’s AI Chips Into a Foreign Policy Tool, With Not a Single Country Being Left Out** (wccftech) - [Read more](https://wccftech.com/the-us-could-soon-turn-nvidia-and-amds-ai-chips-into-a-foreign-policy-tool/) - **Data Center GPU Market Is Going to Boom |• NVIDIA • AMD - openPR.com** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMijwFBVV95cUxOOVRFVExsX29QNTlmUkV2OXo4cFlfVmxhcTVZX2FMNS1ZMjlSQlJrT2dYWVl4eGxjMjdwU1FDNGRzYUtkNWlTTVlNQUlwWkFIaGJjdkhkMnYzY0dnaGF5cjNDZGpQME1EX3ZHMmtCbS0zTWdBelN2SUkyUEZ2dlAtMEtSbzY4ZmJVTjhxeXVCSQ?oc=5) - **US gov't preps sweeping export controls for Nvidia, AMD AI hardware — worldwide licensing system would give Trump admin broad authority to block global sales** (toms_hardware) - [Read more](https://www.tomshardware.com/tech-industry/artificial-intelligence/us-govt-preps-sweeping-export-controls-for-nvidia-amd-ai-hardware-worldwide-licensing-system-would-give-trump-admin-broad-authority-to-block-global-sales) - **Nvidia responds to report that China's DeepSeek is using its banned Blackwell AI chips - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMijAFBVV95cUxNcGxOcmFVX19aUXA0WW9tUzRhd0xBZG9Bamw4Z1VNdzhYZ29PZVNrU0kwN09YdTVMTzZhel8xNkJEZzVCeElCMmFqZXhEZzZSRGtqSUxadFpoQVd0Z0lDM0Jpc0VtWWc0S0xGUW96ZW16bmljb3ByRmszS2UxZDhidldoQWlVS1NGU3NjS9IBkgFBVV95cUxQYzFDdDNwd1RnbG94cXlkRWl2eHpveXFTLTdudVdFOHhuYm1ySnlSWVFFem1UOVRHTHlTdFROTXpqQnNncmNnSFNNdEoxalhLUFpUdllLelU5dXVWMEF5amF2Vk5SLUpEWm4xX3dzVjFUcjI3dmtJSHZOX3k0Q0RoMm45anRHSEhabGlzdWFLalo4Zw?oc=5) - **TSMC Sales Surge. It Might Be an Even Bigger AI Chip Winner than Nvidia. - Barron's** (google_ai_chip) - [Read more](https://news.google.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?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **TSMC Sales Surge. It Might Be an Even Bigger AI Chip Winner than Nvidia. - Barron's** (google_ai_chip) - [Read more](https://news.google.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?oc=5) - **How China's AI chips stack up against Nvidia's H200 - Reuters** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMipwFBVV95cUxOVzYybktZbWExUXk3M1ZaUnVUTDVJQ0hnRUc4SWNSaGlFUVE0aHhueEZLSU9ET1NiX0R3WmVnaXRwVnJsZV95OG5iSTdZV1dLRGRnQjYxOEFocUVYLUdudzE3UUhsdFdfR1JvSHRSZHk1QXBYLWtrSTNIb0dpcmw2TlJVVEVqcXU5Zi1uRU51Y3BqU0tLZy1pSEJkb1d4T09mcG1iMTdGUQ?oc=5) - **Akamai to deploy thousands of Nvidia Blackwell GPUs - Data Center Dynamics** (google_nvidia) - [Read more](https://news.google.com/rss/articles/CBMimwFBVV95cUxNR3huUDNLNFg3RXRNVFNIRGxBd1ZLQ1IwSDV5a3Z5d0RfLTZkYlZ3d1VYRkdHYnVNLWZBU25ETWlVeFEzS1VFVGdvMHJyaWoxQ09hdjE0SDc5NS1BQkloMGNDd3oxM1RmaTk1WW9xUE9hZlBKY1ZmWGZQRU82UmhKRUFhY0EtOTZsSHp0dHZ5ZnVjUmdSc0tkYW5ldw?oc=5) - **AMD Ryzen AI 400 chips will bring newer CPUs, GPUs, and NPUs to AM5 desktops - Ars Technica** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMitAFBVV95cUxPMnR1azdWUjlTa0FfTlZNQUtraXU5aDRoYUVwT0VtRzNHUUpVWVNSeVVIQTFxR0p5LUdzT0lRLWhoOUhuNFkzVWdUMTB4Y0x0Ui1NcXd4a256Q0txNXVKVGFOWGM4dzE0MXRJbDcyU3JuM3I4WWlsMmFfMmlkUk45Mkx2WFJ1b1NBQnh0aEotNHhhNmpsM3UyRkVvWWgzV3FrSXg3UU1YeHE2azNwOW1jbjZfdDg?oc=5) - **Aggressive investments in AI chips and HBM! Asian semiconductor giants' spending this year is expected to reach $136 billion, a 25% increase year-on-year. - 富途牛牛** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMirwFBVV95cUxNQ0Z4bFZmd0pnd0stcEktTTEtajNHWG5lNjlfcDFmb2ZUWTZxOVlseGpwTXBNRm5wbThnN3FiQUhqX0lYSG1ETWdHb2plWVI5TE56MThKOHFfbm1zLVVBNExHODZwRWVYTThRcncwRXBXRFdRYzVMWm1PV0Q3bEJENkFYZm1xYkFsMGVOd0FMUnJ0UnZfNjRGcmNMZUcwd1pYLXlmalQ3S2pQMG9YakVR?oc=5) --- *Sponsored by LimitLess AI*

## Episode Summary In this episode, we cover: - **TSMC Expands AI Chip Production to Japan - 24/7 Wall St.** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMijAFBVV95cUxNaVpZVV9hS0hYTjNrMkt1MkcwZmUyWUY5aXp2Q1NjcF9UUjdKR29RdUI1a0wwX2lwTVpKX0ZKV2VNMzRZZExTaTVLaE8yOUdBbnJtZ3FmVF9CSkVTdldXQTBPUFZQaVh5OW5Db2EzbzQxc0xJd0sxRU9kVnNReDNEZTkyQU5RSnE0T21qNw?oc=5) - **Google's rolling out its most powerful AI chip, taking aim at Nvidia with custom silicon - CNBC** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMiqAFBVV95cUxPRFZ4U1hHVUhsSlRFLTduWXhTMDJEZEx1SVVDUWloZ1BDRGhrVXg4WHdfRGktd2p5eklfTjl4U0pLMjdKLWp5ZkJabXFDTHZEXzFzZnVXdFBzOE95R3RJSU9Ia3dFUzhVSEhaRTVOeS1XVTlEZTVGRFJBTkFzVHJZTEM4ZmEyalJVVV9fZ1NDSkZLQ3BWN2pHSzlmeGlsckVmM053ZjEzUmrSAa4BQVVfeXFMTWR0LVpKYlF0cTZ0cFAweG1reS1Ra2pTMXZzZE9FUEYtRWhocW9tRFNfN1lTQ0JnZnl4TktyVDJ6MG9oZnFraEs3eWprT3ZITkZwUHhlLUUtWmhHTUdsd3Q5bzcxOFpWUFIzRk1BUlFFRWV6Q1RyUEdOQnhiQ1h1a084Sk9UZi1FbnhxWXliNVYtV3BOZmZUZ29GUEdtYlBnd3RrZHZGZkFrYkhDMGl3?oc=5) - **Nvidia-backed photonics startup Ayar Labs fills its wallet to mass-produce CPO chiplets** (the_register) - [Read more](https://go.theregister.com/feed/www.theregister.com/2026/03/03/ayar_labs_500m/) - **Broadcom and TSMC Emerge as ‘Big Winners’ in Custom AI Chip Boom - 24/7 Wall St.** (google_ai_chip) - [Read more](https://news.google.com/rss/articles/CBMiqgFBVV95cUxORVQ4aElvSEVkc3Q5QUNjVmkwSUVZcXg2RWNPdVpEZjBISWZxTUxubjdZam43bmNnb1NFbzd4Wlo4RGxVbkp3SG1tQjdneTRWdjBRWjlaUnFWbmxaaVVtT29ZM2dXbERFTUdnc3dXUmRZNzBWMlBYN0dBb0ZQbzNoTldwemQwNTZQRVVteWNMdDVRbnotS3NqREZlenpOQ0ZQY2RIQXFQR0E0dw?oc=5) - **Meta's reported AI chip pullback seen bolstering Nvidia and AMD while dimming custom silicon push - Proactive financial news** (google_gpu) - [Read more](https://news.google.com/rss/articles/CBMi_AFBVV95cUxPWTVQdWtFcFFkN1l6a3NiT1J3bnRkaVRpbW5fMHZBc3RTVFFhR0lfbndxQmVJNVZoYVEwdzkzRjhsakVObGt6cmxRNDJ0cmJCOU9meXNfYXFTNHZQX0RVV1Q3UW04d0RyMmxkcTVPeDJlRWNubmtxT0V1eUNjczBGdFlQYW42VDNoUWd0VThLUWZXdTJ6a0o1QjNyX2w1cDlyTjNxYV9tRjNMM20zYzZ6OFRxaEJNdmR2WjVOVVRRNEJiYkdOQWJ0Z0ZkX1lBRVE0cEgtUzg5aG9BMEdXVER5YjVxb1RFZmxmVUgwQjNHVC13Rl83S1hSam5fcXA?oc=5) --- *Sponsored by LimitLess AI*