nvidia - The LGTM

The LGTM

Sign in Subscribe

nvidia

A collection of 139 posts

BEVPoolV3 Is the GPU Optimization Physical AI Actually Needs

BEVPoolV3 Is the GPU Optimization Physical AI Actually Needs

Physical AI keeps getting sold from the top of the stack down: humanoids, autonomous vehicles, warehouse robots, spatial computers, “world models,” and whatever phrase survived the keynote draft. NVIDIA’s latest developer post is useful because it starts where production systems usually hurt: a scatter-reduce kernel that has to finish

DFlash Turns Speculative Decoding Into a Blackwell Utilization Story

DFlash Turns Speculative Decoding Into a Blackwell Utilization Story

Speculative decoding is one of those ideas that sounds like a serving hack until you remember the original problem is stranger: we run massively parallel accelerators and then ask large language models to emit text one token at a time. DFlash, the block-diffusion speculative decoding method NVIDIA is now highlighting

Tokens per Watt Is Becoming the AI Factory’s Real P&L Metric

Tokens per Watt Is Becoming the AI Factory’s Real P&L Metric

“Tokens per watt” sounds like a facilities metric until you have to run a real AI product under real capacity limits. Then it becomes the P&L. NVIDIA’s latest AI factory energy-efficiency post is easy to misread as green-computing content. It is really a margin story: every watt

NVIDIA OpenShell Is the Interesting Part of the Agent Toolkit Story

NVIDIA OpenShell Is the Interesting Part of the Agent Toolkit Story

The agent market has spent too much time pretending the hard problem is choosing the smartest model. It is not. The hard problem is giving an agent enough authority to be useful without giving it enough authority to become a root-cause analysis document. NVIDIA’s Agent Toolkit announcement is interesting

NVIDIA and AWS Are Making GPU Retrieval Boring — Which Is Exactly the Point

NVIDIA and AWS Are Making GPU Retrieval Boring — Which Is Exactly the Point

GPU announcements usually arrive dressed as hardware news. This one is more useful if you read it as a retrieval infrastructure story. NVIDIA and AWS are not merely adding another accelerated EC2 shape; they are pushing GPU acceleration into the boring middle of production AI, where vector indexes get rebuilt,

NVIDIA’s Telecom Agents Are a Preview of Production Autonomy With Guardrails

NVIDIA’s Telecom Agents Are a Preview of Production Autonomy With Guardrails

Telecom is where agentic AI demos go to become adults or die quietly. The networks are messy, regulated, latency-sensitive, full of legacy systems and allergic to improvisation. That is why NVIDIA’s DTW Ignite 2026 telecom-agent push is more interesting than the usual “AI agents will run the enterprise” slideware:

NVIDIA’s TOP500 Lead Is an AI-Factory Check, Not a Trophy Case

NVIDIA’s TOP500 Lead Is an AI-Factory Check, Not a Trophy Case

NVIDIA’s latest TOP500 brag sheet is easy to dismiss as another vendor victory lap. Don’t. The useful signal is not that NVIDIA technology appears in 81% of the world’s 500 fastest supercomputers, or that it powers nearly 90% of the systems newly added to the list. The

JUPITER Shows Exascale Science Becoming a Production Workflow

JUPITER Shows Exascale Science Becoming a Production Workflow

Exascale machines used to be covered like trophy cabinets: biggest, fastest, most national-pride-per-rack. JUPITER is more interesting if you ignore the trophy and look at the workloads. Europe’s first exascale supercomputer is being used to train cellular-scale brain models, run kilometer-scale climate simulation, explore 5G and 6G systems, and

Vera at Los Alamos Is NVIDIA’s Reminder That Agents Need CPUs

Vera at Los Alamos Is NVIDIA’s Reminder That Agents Need CPUs

The least fashionable part of agentic AI may be the part that decides whether agents are actually useful: the host CPU. GPUs get the keynote. Models get the benchmark charts. But serious agents spend a suspicious amount of their lives not generating tokens: launching tools, running code, parsing files, starting

NVIDIA’s New Science Stack Moves CUDA-X Into the Lab Control Loop

NVIDIA’s New Science Stack Moves CUDA-X Into the Lab Control Loop

NVIDIA’s latest AI-for-science software drop looks small if you read it like a product announcement: three names, some benchmarks, a few lab examples. Read it like an infrastructure map and it gets more interesting. DAQIRI, ALCHEMI and cuPhoton are NVIDIA pushing CUDA-X out of the accelerator brochure and into

Rubin’s 45°C Liquid Loop Is NVIDIA Turning Cooling Into Token Economics

Rubin’s 45°C Liquid Loop Is NVIDIA Turning Cooling Into Token Economics

NVIDIA’s new Rubin cooling story looks, at first glance, like facilities plumbing: warmer coolant, fewer chillers, less water, cleaner racks. That undersells it. The real announcement is that NVIDIA is trying to make the physical data center part of the AI runtime, because at agent scale the cost of

AWS Trainium Wants to Be a Merchant Chip. NVIDIA’s Moat Is the Software Gravity Around the Chip

AWS Trainium Wants to Be a Merchant Chip. NVIDIA’s Moat Is the Software Gravity Around the Chip

AWS selling Trainium racks outside its own cloud would be more than a product-line expansion. It would be Amazon volunteering for a harder exam: proving its AI silicon can survive outside the managed AWS cocoon, where customers expect not just cheaper tokens but debuggable compilers, boring operations, mature frameworks, predictable