Subscribe
Sign in
Home
Main Site
Models & Research
Die Yield Calculator
Compliance
Archive
About
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
74
1
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
100
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
132
10
Most Popular
View all
Claude Code is the Inflection Point
Feb 5
•
Doug O'Laughlin
,
Jeremie Eliahou Ontiveros
,
Jordan Nanos
,
Dylan Patel
, and
Daniel Nishball
553
6
81
TPUv7: Google Takes a Swing at the King
Nov 28, 2025
•
Dylan Patel
,
Myron Xie
,
Daniel Nishball
,
Wei Zhou
,
Jeremie Eliahou Ontiveros
,
Ivan Chiam
,
Cheang Kang Wen
,
Clara Ee
,
Wega Chu
,
Kimbo Chen
,
AJ
, and
Michael Chen
408
10
43
Microsoft's AI Strategy Deconstructed - From Energy to Tokens
Nov 12, 2025
•
Jeremie Eliahou Ontiveros
,
Dylan Patel
,
Myron Xie
,
Wei Zhou
,
Jordan Nanos
,
Clara Ee
,
Daniel Nishball
, and
AJ
246
13
27
OpenAI Jalapeño: Better Than Nvidia Blackwell
Aug 25
•
Bryan Shan
,
Myron Xie
,
Jordan Nanos
,
Wega Chu
,
Clara Ee
, and
Dylan Patel
275
2
30
Co-Packaged Optics (CPO) Book – Scaling with Light for the Next Wave of Interconnect
Jan 1
•
Dylan Patel
,
Daniel Nishball
,
Myron Xie
,
Ivan Chiam
,
Clara Ee
, and
Patrick Zhou
304
4
39
Gemini is Cooked but GCP is Cooking
Aug 7
•
Max Kan
,
Joey Brookhart
,
Doug O'Laughlin
, and
Dylan Patel
324
9
30
Latest
Top
Discussions
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
90
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
142
4
11
See all
SemiAnalysis
Bridging the gap between the world's most important industry, semiconductors, and business.
Subscribe
Recommendations
View all 15
Nongaap Investing
Mike
D2D Newsletter
Digits to Dollars
The Chip Letter
Babbage
The Algorithmic Bridge
Alberto Romero
Artificial Intelligence Made Simple
Devansh
SemiAnalysis
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts