A developer describes running ~50 local AI agents on a single 6GB GPU by using a lock-based queue, an eviction monitor, a resource governor, and a model router. The system serializes GPU access so onl…
InfiniBand, a high-performance interconnect technology designed for Remote Direct Memory Access (RDMA), has become critical for AI training and inference workloads that require direct data movement be…
Micron Technology is set to report fiscal Q3 2026 earnings on June 24, projecting record revenue of $33.5B and a non-GAAP gross margin of 81%, more than double from a year ago, driven by surging deman…
HIVE Digital Technologies announced a CAD $3.5 billion AI gigafactory in the Greater Toronto Area, aiming to support Canada's goal of 850 MW of sovereign compute by 2030. The 320 MW facility, expected…
Nvidia demonstrated an agentic robotics system called ENPIRE that taught fleets of robots to perform dexterous tasks, including handing a GPU to another arm and positioning it over a motherboard. The …
MarkTechPost published a tutorial on building memory-efficient Transformers using xFormers, covering packed sequences, grouped-query attention, ALiBi, SwiGLU, and causal attention. The guide demonstra…
OpenAI spent $3.7 billion in Q1 2026, tripling its cash burn year-over-year, while revenue reached $5.7 billion. The company holds $73 billion in cash and securities after a $122 billion funding round…
A developer achieved 2678x faster matrix multiplication using a GPU with CUDA, demonstrating how parallel processing on thousands of GPU cores reduces the O(N³) complexity of sequential matrix multipl…
A technical analysis calculates the dollar cost per user for serving large language models at scale using napkin math, breaking down GPU resources, matrix multiplication costs, and attention mechanism…
A developer building Pixova's free AI image generator implemented an async job queue pattern to connect a Next.js frontend to a GPU inference endpoint, avoiding timeout issues from long-running HTTP c…
JAX's default_device context manager places arrays on the specified device but does not commit them, allowing JAX to move them to other devices. This caused array lookups to take over a second by trig…
Shrijith Venkatramana, developer of git-lrc, explains how kernel fusion reduces memory bandwidth bottlenecks in LLM inference. By combining multiple GPU operations into a single kernel, intermediate d…
Microsoft released Windows Subsystem for Linux (WSL) 3 as a beta preview at Build 2026, introducing paravirtualization to give Linux direct access to GPUs and NPUs without performance overhead. The up…
Agentic AI workloads are shifting the compute ratio, making CPUs the critical coordination substrate rather than a support component for GPUs. This inversion is exposed by current Xeon supply tightnes…
Carmen Li, CEO of Silicon Data and Compute Exchange, said the compute market is shifting from on-demand to forward contracts as GPU price volatility rises, with fungibility challenges complicating tra…
A comprehensive list of 33 metrics for evaluating large language models (LLMs) has been compiled, covering performance indicators such as time to first token, average tokens per second, throughput, er…
A Hacker News user asks the community how they choose between GPU rental providers for machine learning workloads, questioning whether price, reliability, or setup environment is the deciding factor w…
Neurophos announced its Optical Processing Unit (OPU), a photonic AI chip achieving 0.47 ExaOPS at 300 TOPS/W, claiming 10,000x size reduction over traditional photonic tensor cores. The company says …
IREN has secured a $3.65 billion GPU financing facility to support Microsoft's AI cloud expansion. The deal will provide the necessary infrastructure for scaling AI workloads in Microsoft's cloud serv…
Anjney Midha, founder and CEO of AMP, said AI development is consuming unprecedented resources and that big companies dominate the landscape due to their ability to justify massive spending on AGI. He…