保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

SubscribeSign in Home Main Site Models & Research Die Yield Calculator Compliance Archive About

Page not found

LatestTopDiscussions How GLM5.3 Sparse Attention Affects HBM Memory Usage GLM-5.3, KV Cache Offloading, HiSparse, AgentX TileRT, InferenceX DeepSeek Sparse Attention, IndexShare, Single-rollout Asynchronous Optimization… Sep 28 • Kimbo Chen, Alec Ibarra, Wenyao Gao, Pratt Bhatt, Bryan Shan, and Dylan Patel 80 2 Intel Panther Lake Teardown Taking a look inside Intel’s latest consumer chip and 18A process node Sep 26 • Adith Shankar, Daniel Sanchez, Allison Elliott, Sarah Lawrence, Afzal Ahmad, Andrew Wagner, STEEL Team, and Dylan Patel 103 8 The Chinese AI Infrastructure Boom: Introducing the SemiAnalysis China Datacenter Model 1,000+ facilities across 60+ operators mapped, built retail-first and flipped by AI, largest hyperscaler leases 1/5 national capacity, 100MW in 12… Sep 25 • Everlyn, Dylan Patel, and Patrick Schaabi 136 12 ClusterMAX 3.0: The Industry Standard GPU Cloud Rating System Returns In gory detail: reliability, performance, support, pricing—and, of course, security—in our most thorough analysis of GPU cloud providers globally. Sep 23 • Jordan Nanos, Sam Harshe, Samuel Kruse, Pratt Bhatt, Billy Cao, Jack Carson, and Dylan Patel 91 9 Computation and Data Movement for Inference Mapping MoE models onto inference hardware: structure, flow, and efficient serving Sep 21 • Tanj Bennett, Bryan Shan, and Dylan Patel 217 7 Engrams Embedding Entendre: Codesign for Efficient DRAM/SSD Offloading New Model Architecture Implications for TAM of DRAM/NVMe, DeepSeek V4.1 Flash, AgentX, InferenceX, NVMe experiments Sep 18 • Bryan Shan, Cam Quilici, Alec Ibarra, Kimbo Chen, Myron Xie, and Dylan Patel 94 5 Everyone Says Datacenter Moratoriums Are Killing the US Buildout. We disagree 300+ moratoriums mapped, 20GW sits inside a restricted local boundary, 1,525MW actually slips, 2.3GW nationwide including New York Sep 15 • Maya Barkin, Reyk Knuhtsen, Jeremie Eliahou Ontiveros, and Dylan Patel 138 12 Vera Rubin NVL72 Agentic Inference: 67x better Performance per Dollar Jensen Sandbagging Performance Again, 2x more Annual Profit Per GigaWatt, The More you Buy, The More you Earn, AgentX, InferenceX, Extreme Co-Design Sep 14 • Bryan Shan, Alec Ibarra, Cam Quilici, Wenyao Gao, and Dylan Patel 100 6 9 A Brain Too Big to Carry — On-Device vs Datacenter Inference Robot Models, Silicon & DRAM Efficiency, Jetson Thor vs. B300 TCO, Deployments, The Network Wall Sep 14 • Ivan Chiam, Gianluca Bencomo, Zane Fong, Bryan Shan, Dylan Patel, and Reyk Knuhtsen 170 2 10 Long Live the Short King: Why 4-hi HBM Wins Same Bandwidth, Fewer Dies: How 4-hi HBM Cuts Inference Costs and Makes Scarce DRAM Go Further Sep 13 • Myron Xie, Bryan Shan, Harrison Barclay, Minjae Kang, and Dylan Patel 143 4 11 Nvidia’s Backstop Universe – Heads I Win, Tails Who Loses? The $11T AI Buildout, Nvidia’s Backstop Economics, and the Limits of Nvidia’s Balance Sheet Sep 11 • Daniel Nishball, Oliver Kennon, and Terence Ong 132 2 7 What is So Hard About Behind-The-Meter Power For Datacenters? Part 1 Dumb Science Experiments vs. Money Printing Machines Sep 10 • Ellie Holbrook, Robert Boswall, Jeremie Eliahou Ontiveros, Nicolas Bontigui, and Dylan Patel 145 2 13 TPU Inference Externalization Full Steam Ahead - InferenceX InferenceX, Up to 50% Better Performance per Dollar, Rapid Externalization of TPU stack, Growing Customer Base, Ironwood, TPUv8i, Reducing CUDA Moat Sep 7 • Alec Ibarra, Cam Quilici, Bryan Shan, Wenyao Gao, Daniel Nishball, Zane Fong, and Dylan Patel 128 1 10 Korea’s Trillion-Dollar Sovereign AI Investment: Nvidia Wins, Hynix Loses Korea hosts a Squid Games, National AI Tournament, the best non-Chinese open source model gets eliminated, why Nvidia needs open source, implications… Sep 1 • Max Kan, Ray Wang, Myron Xie, and Dylan Patel 187 2 14

August 2026

Most Neoclouds Suck At Security OpenAI vs HuggingFace, Container Escapes, Kernel Bypass, Network Policies, Security Keys, Multi-tenant Grafana, and a ClusterMAX 3.0 Preview Aug 30 • Jordan Nanos, Sam Harshe, Pratt Bhatt, Billy Cao, Jack Carson, and Dylan Patel 147 5 9 OpenAI Jalapeño: Better Than Nvidia Blackwell OpenAI’s self-designed ASIC compared with Rubin, Jalapeño’s TCO, throughput per MW, and spicy deets Aug 25 • Bryan Shan, Myron Xie, Jordan Nanos, Wega Chu, Clara Ee, and Dylan Patel 275 2 30 AgentX - InferenceXv3: Does CUDA Moat Hold up in Agentic Inferencing? $3 Million USD dataset open sourced, 1 Mil+ Context Length, Multiturn, Sub Agents 95%+ KVCache HitRate, GB300 NVL72, MI355, B200 Aug 24 • Cam Quilici, Bryan Shan, Alec Ibarra, Daniel Nishball, Zane Fong, Kimbo Chen, and Dylan Patel 89 1 8 Are Open Models Catching Up? Comparing open vs. closed models across the eras of frontier models, Is the gap narrowing? Aug 21 • Evan Cloutier, Max Kan, Jordan Nanos, and Dylan Patel 255 4 29 Cerebras's Next Generation CS-4: Fast Just Got Faster Double the Performance, Double the Power, Double the Fun Aug 19 • Myron Xie, Bryan Shan, Wega Chu, Jordan Nanos, and Dylan Patel 142 1 6 $12B of US ratepayers' money wasted on a modeling mistake and PJM wants to do it again American Grid design needs an overhaul, Why it is good to be full of cold air. Aug 16 • Robert Boswall, Reyk Knuhtsen, Jeremie Eliahou Ontiveros, Oliver Kennon, Dylan Patel, and Dashboard American 119 4 9 Ultra-High Interactivity on NVIDIA GPUs? - TileRT InferenceX Can TileRT software on NVIDIA GPU compete with Cerebras, Groq LPU, SambaNova? Batch Size 1, Disaggregated engine, high throughput prefill engine, high… Aug 10 • Bryan Shan, Daniel Nishball, Cam Quilici, Kimbo Chen, Alec Ibarra, and Dylan Patel 148 1 6 SpaceX 10GW in 2027 – Why It’s Real, Will Drive $300B ARR for SpaceX, and Why Microsoft Will Be the Largest Offtaker Inference at 100B/GW/year, SpaceX's stellar pace, Microsoft's 10GW 2026 Awakening, Azure Can Grow Triple-Digits Aug 7 • Jeremie Eliahou Ontiveros, Reyk Knuhtsen, Jordan Nanos, Max Kan, Dylan Patel, and Muhammad Zuhair 302 11 20 Gemini is Cooked but GCP is Cooking GCP YoY rev growth >100%, DeepMind's long term failure is Google Cloud's short term gain Aug 7 • Max Kan, Joey Brookhart, Doug O'Laughlin, and Dylan Patel 324 9 30 Kimi K3, The Manos, The Mythos, The Legendos Kimi K3’s architecture: compressed memory, attention across depth, latent expert routing, and serving performance Aug 3 • Kimbo Chen, Shubham Choudhari, Bryan Shan, and Dylan Patel 176 12 © 2026 Dylan Patel · Privacy ∙ Terms ∙ Collection notice Start your SubstackGet the app Substack is the home for great culture