#groq-lpu-technology

[ follow ]
#broadcom
Tech industry
from24/7 Wall St.
1 hour ago

Broadcom's Long-Term Google TPU Deal Is Bigger Than It Looks for AI Infrastructure

Broadcom's long-term agreement with Alphabet for custom TPUs enhances revenue visibility and positions the company for significant growth in AI semiconductor revenue.
fromTheregister
16 hours ago
Tech industry

Anthropic reveals $30bn run rate, plan to use new Google TPU

Broadcom will develop next-gen AI chips for Google and supply components for AI racks, with Anthropic set to consume 3.5GW of TPUs.
Tech industry
from24/7 Wall St.
1 hour ago

Broadcom's Long-Term Google TPU Deal Is Bigger Than It Looks for AI Infrastructure

Broadcom's long-term agreement with Alphabet for custom TPUs enhances revenue visibility and positions the company for significant growth in AI semiconductor revenue.
Tech industry
fromTheregister
16 hours ago

Anthropic reveals $30bn run rate, plan to use new Google TPU

Broadcom will develop next-gen AI chips for Google and supply components for AI racks, with Anthropic set to consume 3.5GW of TPUs.
#ai
fromTechCrunch
1 hour ago
Artificial intelligence

Anthropic ups compute deal with Google and Broadcom amid skyrocketing demand | TechCrunch

fromTechCrunch
6 days ago
Silicon Valley

Cognichip wants AI to design the chips that power AI, and just raised $60M to try | TechCrunch

Artificial intelligence
fromTechCrunch
1 hour ago

Anthropic ups compute deal with Google and Broadcom amid skyrocketing demand | TechCrunch

Anthropic signed a new agreement with Google and Broadcom to expand compute capacity for its Claude AI models amid soaring demand.
Data science
fromTheregister
3 days ago

PrismML debuts 1-bit LLM in bid to free AI from the cloud

PrismML's Bonsai 8B is a 1-bit language model that outperforms larger models, enhancing AI efficiency for mobile applications.
Data science
fromTheregister
5 days ago

TurboQuant is a big deal, but it won't end the memory crunch

TurboQuant is an AI data compression technology that reduces memory usage for KV caches but may not significantly alleviate memory shortages.
Silicon Valley
fromTechCrunch
6 days ago

Cognichip wants AI to design the chips that power AI, and just raised $60M to try | TechCrunch

Cognichip aims to revolutionize chip design using AI, significantly reducing costs and timelines in the semiconductor industry.
#intel
fromWIRED
1 day ago
Tech industry

The Ridiculously Nerdy Intel Bet That Could Rake in Billions

Business
from24/7 Wall St.
4 days ago

Intel Climbs 4% as AI Hardware Momentum and Fab Buyback Make the Bull Case Hard to Dismiss

Intel's stock rises due to a significant buyback and growth in AI hardware, reflecting strong financial health and operational autonomy.
Tech industry
fromWIRED
1 day ago

The Ridiculously Nerdy Intel Bet That Could Rake in Billions

Intel is investing heavily in advanced chip packaging to capitalize on the AI boom and compete with Taiwan Semiconductor Manufacturing Corporation.
Business
from24/7 Wall St.
2 weeks ago

Is Intel Back in the AI Race? What's Changing the Narrative

Intel's stock has surged 91.46% in a year, driven by AI edge initiatives and a strong supply chain strategy.
Tech industry
from24/7 Wall St.
3 days ago

Intel's Panther Lake Chip is Seriously Impressive. It's Time to Buy the Stock

Intel's stock has surged nearly 130% under CEO Lip-Bu Tan, signaling a potential comeback in the chip industry.
#rowhammer
Information security
fromSecurityWeek
5 hours ago

GPUBreach: Root Shell Access Achieved via GPU Rowhammer Attack

A new Rowhammer attack, GPUBreach, allows privilege escalation and memory corruption in GPUs, posing significant threats to cloud environments.
Information security
fromSecurityWeek
5 hours ago

GPUBreach: Root Shell Access Achieved via GPU Rowhammer Attack

A new Rowhammer attack, GPUBreach, allows privilege escalation and memory corruption in GPUs, posing significant threats to cloud environments.
#nvidia
fromFortune
1 day ago
Silicon Valley

Supermicro soared because of $4 trillion Nvidia-and Jensen Huang can walk away any time he wants | Fortune

Business
from24/7 Wall St.
2 days ago

The 1 Stat That Proves Nvidia Remains a Screaming Buy Below $200

Nvidia's operating income surged to $130.4 billion in fiscal 2026, indicating strong growth potential and making the stock an attractive entry point for investors.
Video games
fromGadgets 360
6 days ago

Nvidia Brings New AI Features With a New DLSS 4.5 Update

Nvidia's DLSS 4.5 update introduces 6X multi-frame generation and dynamic multi-frame generation for enhanced gaming performance.
Software development
fromArs Technica
5 days ago

Nvidia rolls out its fix for PC gaming's "compiling shaders" wait times

Nvidia's new Auto Shader Compilation feature allows automatic shader compilation during idle times to reduce load times for PC gamers.
Silicon Valley
fromFortune
1 day ago

Supermicro soared because of $4 trillion Nvidia-and Jensen Huang can walk away any time he wants | Fortune

A scandal involving Supermicro's co-founder threatens the long-standing partnership with Nvidia, impacting their collaboration in the AI sector.
Venture
from24/7 Wall St.
5 days ago

NVIDIA Just Made Another Big Bet-Are You Still Paying Attention?

Nvidia invested $2 billion in Marvell Technology, continuing its trend of significant investments in the AI sector.
#ibm
DevOps
fromComputerWeekly.com
5 days ago

Arm works with IBM to deliver flexibility on mainframe | Computer Weekly

IBM and Arm are collaborating to create dual-architecture hardware for enterprise AI and data-intensive workloads.
DevOps
fromComputerWeekly.com
5 days ago

Arm works with IBM to deliver flexibility on mainframe | Computer Weekly

IBM and Arm are collaborating to create dual-architecture hardware for enterprise AI and data-intensive workloads.
Science
fromNature
5 days ago

Breakthrough computer chip tech could help meet 'monumental demand' driven by AI

A new light source enables the creation of 8 nm wide structures on silicon wafers, increasing transistor density for advanced computer chips.
Venture
from24/7 Wall St.
3 days ago

Why Marvell's Breakout Deserves Investors' Attention

Marvell stock shows potential for long-term growth following Nvidia's $2 billion investment, despite short-term market fluctuations.
Scala
fromInfoQ
5 days ago

Beyond RAG: Architecting Context-Aware AI Systems with Spring Boot

Context-Augmented Generation (CAG) enhances Retrieval-Augmented Generation (RAG) by managing runtime context for enterprise applications without requiring model retraining.
Tech industry
from24/7 Wall St.
2 hours ago

Micron's AI Memory Boom Is Real-And Analysts Are Still Playing Catch Up

Micron shares remain volatile amid questions about memory demand due to AI efficiency gains and potential supply shortages into the 2030s.
fromTechzine Global
5 days ago

IGEL OS can now run AI models locally on endpoints

AI Armor provides dynamic runtime security and relies on a central policy engine in the Universal Management Suite (UMS) to meet compliance requirements, ensuring that organizations can manage their security effectively.
DevOps
Tech industry
fromTNW | Anthropic
11 hours ago

Anthropic signs biggest compute deal yet with Google and Broadcom as run rate hits $30bn | TNW

Anthropic secures 3.5 gigawatts of Google TPU capacity via Broadcom, marking a significant infrastructure commitment and revenue growth surpassing $30bn.
Silicon Valley
fromSilicon Canals
4 days ago

Frugal AI wants to break the global compute hierarchy before it becomes permanent - Silicon Canals

The Soliga tribe's speech AI system exemplifies a new, decentralized approach to AI that challenges existing global tech hierarchies.
Business
from24/7 Wall St.
5 days ago

Lumentum's Path to $1,000 per Share Runs Straight Through the AI Optics Boom

Lumentum Holdings is a key player in AI infrastructure, providing essential optical components for data centers, with significant stock growth and future potential.
Information security
fromTechRepublic
6 days ago

Google Warns Quantum Computers Could Crack Crypto Sooner Than Expected

Quantum computing poses an imminent threat to cryptocurrency security, with fewer resources needed to break current cryptographic protections than previously estimated.
DevOps
fromApp Developer Magazine
6 days ago

Lens Launches MCP Server to Connect AI Coding Assistants with Kubernetes

Lens by Mirantis integrates a Model Context Protocol server, simplifying AI coding assistants' access to Kubernetes clusters.
Gadgets
fromTheregister
3 weeks ago

Lightmatter says latest photonics will halve DC fiber bill

LightMatter's Passage L20 optical engine reduces datacenter fiber usage by half using near-package integration instead of co-packaging, positioning between pluggable modules and co-packaged optics.
#arm-holdings
from24/7 Wall St.
3 days ago
Tech industry

Arm Holdings: The Chip Designer Drawing NVIDIA Comparisons-Is It Justified?

Arm Holdings' AGI CPU release has sparked significant market interest, raising questions about its competitive position in the tech industry.
Tech industry
from24/7 Wall St.
3 days ago

Arm Holdings: The Chip Designer Drawing NVIDIA Comparisons-Is It Justified?

Arm Holdings' AGI CPU release has sparked significant market interest, raising questions about its competitive position in the tech industry.
fromArs Technica
3 weeks ago

Intel shores up its desktop CPU lineup with boosted Core Ultra 200S Plus chips

The Core Ultra 200S Plus processors (also referred to as Arrow Lake Refresh, in some circles) add more processor cores, boost clock speeds, add support for faster memory, and speed up the internal communication between different parts of the processor. Collectively, Intel says these improvements will boost gaming performance by an average of 15 percent.
Video games
Gadgets
fromTheregister
3 weeks ago

Ayar Labs, Wiwynn to cram 1,024 GPUs into photonic system

Ayar Labs and Wywinn are developing a rack-scale platform using silicon photonics to connect over 1,024 GPUs with significantly lower power consumption than copper-based systems.
#arm
Tech industry
fromWIRED
2 weeks ago

Arm Is Now Making Its Own Chips

Arm is producing its own semiconductors, marking a shift from licensing to manufacturing in response to AI demand.
Tech industry
fromWIRED
2 weeks ago

Arm Is Now Making Its Own Chips

Arm is producing its own semiconductors, marking a shift from licensing to manufacturing in response to AI demand.
Mobile UX
fromTheregister
1 month ago

Qualcomm, Nvidia push 'AI-native' 6G - definition pending

Major tech companies are announcing 6G commercialization plans at Mobile World Congress, positioning AI as the primary catalyst for the next generation of wireless networks, despite binding 6G standards remaining undeveloped.
Gadgets
fromTechzine Global
4 weeks ago

AMD is giving its embedded chips 80 TOPS of AI compute

AMD's expanded Ryzen AI Embedded P100 Series delivers up to 12 Zen 5 cores and 80 system TOPS for industrial, robotics, and medical imaging applications with ROCm software support.
#meta
Artificial intelligence
fromMedium
2 weeks ago

Less Compute, More Impact: How Model Quantization Fuels the Next Wave of Agentic AI

Model quantization and architectural optimization can outperform larger models, challenging the belief that more GPUs equal greater intelligence.
Tech industry
fromComputerWeekly.com
5 days ago

Marvell scales up networking to extend Nvidia AI ecosystem | Computer Weekly

Marvell Technology joins Nvidia AI ecosystem to enhance infrastructure development with a $2bn investment.
Artificial intelligence
fromTechzine Global
3 weeks ago

Nvidia's Groq 3 LPU targets agentic AI inference at GTC 2026

Nvidia's acquisition of Groq technology produces the Groq 3 LPU, a specialized inference chip delivering 40 petabytes per second bandwidth, significantly outpacing GPU inference speeds.
Venture
from24/7 Wall St.
1 month ago

Even Nvidia Sees Lumentum as Lighting the Way Forward

Nvidia invests $2 billion in Lumentum through a strategic partnership to secure advanced optical components for next-generation AI data centers and gigawatt-scale infrastructure.
Artificial intelligence
fromTechCrunch
3 weeks ago

Niv-AI exits stealth to wring more power performance out of GPUs | TechCrunch

AI data centers waste significant power due to GPU demand surges, forcing operators to throttle performance by up to 30%, prompting startups like Niv-AI to develop precision power management solutions.
Tech industry
fromTechzine Global
1 week ago

Arm Launches 136-Core AGI CPU for Data Centers

Arm introduces the Arm AGI CPU, designed for AI data centers with significant performance improvements and capacity requirements.
Tech industry
fromThe Verge
1 week ago

Arm's first CPU ever will plug into Meta's AI datacenters later this year

Arm AGI CPU features up to 136 cores and claims double the performance per watt compared to x86 chips.
fromTechRepublic
3 weeks ago

Meta's New AI Chips Reveal a Faster, More Self-Reliant Hardware Strategy

Meta is building these chips because buying AI hardware at scale is expensive, and relying too heavily on external suppliers leaves less room to shape that hardware to its own needs. Building more in-house could help the company keep AI costs in check.
Artificial intelligence
fromTheregister
1 week ago

Alibaba delivers RISC-V server chip optimized for Chinese AI

The XuanTie C950 is equipped with a self-developed AI acceleration engine, and for the first time natively supports large models with hundreds of billions of parameters, such as Qwen3 and DeepSeek V3, potentially becoming a new type of high-end CPU for the AI Agent era.
Tech industry
Tech industry
fromTheregister
2 weeks ago

A closer look at Nvidia's Groq-powered LPX rack systems

Nvidia acquired Groq for $20 billion primarily to accelerate time-to-market for SRAM-heavy inference chips rather than develop the technology independently, enabling faster token generation for AI reasoning workloads.
Tech industry
fromTechzine Global
2 weeks ago

Cisco Silicon One combines uniform chip design with specific deployments

Cisco's Silicon One G300 is a 102.4 terabit networking chip designed for advanced AI data center infrastructure.
Tech industry
fromTheregister
3 weeks ago

Nvidia slaps Groq into new LPX racks for faster AI response

Nvidia integrates Groq's language processing units into Vera Rubin systems to dramatically accelerate LLM inference, enabling hundreds to thousands of tokens per second per user.
Artificial intelligence
fromTechzine Global
1 month ago

Nvidia is working on a chip for AI inferencing with Groq technology

Nvidia is developing an energy-efficient inferencing chip using Groq technology to compete in AI inference processing, with OpenAI as an early customer.
Tech industry
fromComputerworld
3 weeks ago

System-level 'coopetition': Why Nvidia's DGX Rubin NVL8 runs on Intel Xeon 6

Nvidia's flagship DGX Rubin NVL8 AI systems use Intel Xeon 6 processors as host CPUs to maintain x86 compatibility and meet enterprise deployment requirements.
Tech industry
fromAxios
3 weeks ago

Nvidia's race to outpace physics

Nvidia CEO projects at least $1 trillion in revenue from newest chips through 2027, though market dominance has declined from 100% to 65% as energy efficiency becomes critical to AI scaling.
Tech industry
fromBusiness Insider
3 weeks ago

Nvidia sees a $1 trillion opportunity through 2027 - and it's pushing further into a hot AI field

Nvidia unveiled the Groq 3 LPX inference system, integrating Groq technology to accelerate inference workloads by 35 times, shipping in late 2024.
Tech industry
fromZDNET
3 weeks ago

Nvidia wants to own your AI data center from end to end

Nvidia expanded its AI infrastructure portfolio with five rack types, including a new LPX inference rack using Groq technology, positioning itself to control all data center processing.
Tech industry
from24/7 Wall St.
3 weeks ago

Nvidia GPU availability near zero, AI compute demand off the charts

GPU availability is near zero, indicating demand from hyperscalers and enterprises far exceeds supply, validated by Nvidia's 73% revenue growth and 75% data center revenue increase.
Tech industry
fromThe Verge
1 month ago

Nvidia's spending $4 billion on photonics to stay ahead of the curve in AI

Nvidia invests $2 billion each in Lumentum and Coherent to develop photonics technology for AI data centers, improving energy efficiency and data transfer speeds through optical components.
fromTechCrunch
2 months ago

Quadric rides the shift from cloud AI to on-device inference - and it's paying off | TechCrunch

The company, which is based in San Francisco and has an office in Pune, India, is targeting up to $35 million this year as it builds a royalty-driven on-device AI business. That growth has buoyed the company, which now has post-money valuation of between $270 million and $300 million, up from around $100 million in its 2022 Series B, Kheterpal said.
Artificial intelligence
Artificial intelligence
fromwww.infoworld.com
2 months ago

Google's LiteRT adds advanced hardware acceleration

LiteRT delivers 1.4× faster GPU performance than TFLite, unifies GPU and NPU workflows, enables cross-platform deployment via ML Drift, and supports PyTorch/JAX model conversion.
fromTheregister
2 months ago

Unpacking AMD's latest datacenter CPU and GPU announcements

AMD clarified those estimates are based on a comparison between an eight-GPU MI300X node and an MI500 rack system with an unspecified number of GPUs. The math works out to eight MI300Xs that are 1000x less powerful than X-number of MI500Xs. And since we know essentially nothing about the chip besides that it'll ship in 2027, pair TSMC's 2nm process tech with AMD's CDNA 6 compute architecture, and use HBM4e memory, we can't even begin to estimate what that 1000x claim actually means.
Artificial intelligence
Artificial intelligence
fromTechzine Global
2 months ago

OpenAI seeks faster alternatives to Nvidia chips

OpenAI seeks alternative inference chips with larger on-chip SRAM to improve response speed for coding and AI-to-AI communication, aiming for about 10% of future inference capacity.
[ Load more ]