AI Hardware
Taalas Hardwired AI Chips Hit 17K Tokens Per Second
Startup Taalas is challenging GPU dominance with hardwired AI chips designed specifically for inference, claiming 17,000 tokens per second throughput for ubiquitous AI deployment.
AI Hardware
Meta
Meta Secures Millions of Nvidia AI Chips in Major Deal
Meta has struck a major deal with Nvidia to acquire millions of next-generation AI chips, dramatically expanding its compute infrastructure for AI model training and deployment.
AI Hardware
Positron Raises $230M to Challenge Nvidia's AI Chip Dominance
Startup Positron secures $230M Series B to develop alternative AI chips, potentially reshaping the hardware landscape that powers video generation and synthetic media systems.
AI Hardware
DABench-LLM: New Framework Benchmarks Post-Moore AI Accelerators
Researchers introduce DABench-LLM, a standardized framework for evaluating dataflow AI accelerators designed for large language model inference in the post-Moore era.
Microsoft
Microsoft Unveils Maia 200 AI Chip to Challenge Amazon and Google
Microsoft announces its Maia 200 custom AI accelerator, entering direct competition with Amazon and Google in the race to build proprietary silicon for AI workloads.
Apple
Apple Reportedly Building AI Wearable to Compete with OpenAI
Apple is developing an AI-powered wearable device, responding to OpenAI's hardware ambitions. The move signals intensifying competition in AI interfaces beyond smartphones.
AI Hardware
Micron: AI Memory Chip Shortage to Extend Past 2026
Micron declares AI-driven memory shortage 'unprecedented,' predicting supply constraints will persist beyond 2026 as demand for high-bandwidth memory outpaces production capacity.
AI Hardware
Groq's LPU Architecture: Why Deterministic Compute Matters for AI
Groq's Language Processing Unit takes a radically different approach to AI inference, replacing GPU parallelism with deterministic compute for predictable, ultra-fast performance.
AMD
AMD's AIE4ML Framework: Compiling Neural Networks for NPUs
AMD researchers unveil AIE4ML, an end-to-end compiler framework that maps neural networks to next-gen AI Engines, achieving significant speedups over CPU implementations for ML workloads.
LLM Infrastructure
FPGA-Based CXL Memory Architecture Tackles LLM KV-Cache Bottlenec
New research proposes CXL-SpecKV, a disaggregated FPGA architecture using CXL memory pooling and speculative prefetching to overcome memory bottlenecks in large language model inference at datacenter scale.
AI Hardware
Apple Silicon ML Benchmarks Reveal Local AI Media Power
New benchmarks of Apple's MLX framework demonstrate the growing capability of on-device AI processing, with major implications for local synthetic media generation.