Hardware & Compute
Chips, data centres and the infrastructure behind AI.
-
Amazon Trainium3 vs Google Trillium: AI training chip comparison
Amazon’s Trainium3 offers 30 to 40 percent more price-performance than its predecessor, while Google’s Trillium provides 4x training performance improvements for models…
-
AMD MI350X vs Intel Gaudi 3: TCO for Llama 4 Clusters
AMD’s MI350X offers superior VRAM capacity and bandwidth for Meta’s Llama 4 Maverick models compared to Intel Gaudi 3. While Gaudi 3…
-
High-efficiency inference with Positron Atlas
The Positron Atlas accelerator delivers 280 tokens per second per user for Llama 3.1 8B while using only 33% of the power…
-
NVIDIA Blackwell Ultra supply chain risks and OpenAI Stargate delivery
OpenAI’s $500 billion Stargate project faces critical delivery risks from TSMC CoWoS packaging bottlenecks, HBM memory shortages, and regulatory delays in New…
-
TSMC A16 yields and Intel 18A capacity for AI accelerators
TSMC maintains a manufacturing lead with N2 yield rates between 70% and 80%, while Intel’s 18A process targets low defect density for…
-
The memory wall and the Cerebras Wafer Scale Engine 3
The Cerebras WSE-3 overcomes the memory wall by providing 21 petabytes per second of on-chip bandwidth. This wafer-scale architecture delivers significantly higher…
-
How to get started with Modular’s MAX Engine for Apple Silicon
Learn how to deploy LLMs and diffusion models using the Modular MAX engine on Apple M-series chips. The M5 chip provides up…
-
Groq LPU vs SambaNova SN40L: Llama 4 inference comparison
SambaNova’s SN40L outperforms Groq’s LPU for Llama 4 Maverick deployments by utilizing a three-tier memory system. While Groq requires 576 chips for…
-
The history of NVIDIA NVLink from Kepler to Blackwell Ultra
Trace the evolution of NVIDIA NVLink from the 160 GB/s Tesla P100 to the 3.6 TB/s Vera Rubin platform. This technical history…
-
Tesla shifts from Dojo to AI6 training clusters
Elon Musk has disbanded the Dojo team in favor of the AI6 chip architecture, which scales from FSD to Optimus. This strategic…
-
Why Cerebras’s Andromeda supercomputer matters for OpenAI
OpenAI has invested $10 billion in Cerebras to address inference bottlenecks for models like GPT-5. The Andromeda supercomputer utilizes wafer architecture to…
-
Lightmatter’s Passage photonic interconnect and NVIDIA Blackwell
Lightmatter’s Passage M1000 photonic interposer provides 114 Tbps of bidirectional bandwidth to solve chiplet communication bottlenecks. This technology integrates with NVIDIA’s Blackwell…
Trending Now
- How to use Harvey’s $715M AI legal assistant for Big Law workflows
- The economics of Devin and the shift from replacement to task delegation
- Perplexity valuation hits $3 billion as enterprise demand scales
- The Google DeepMind evolution and the $500B infrastructure race
- How Wayve’s embodied AI model scales autonomous vehicle partnerships