SDxCentral

AI inference crisis: Google engineers on why network latency and memory trump compute

Google researchers have warned that large language model (LLM) inference is hitting a wall amid fundamental problems with memory and networking problems, not compute. In a paper authored by ...
Semiconductor Engineering

Silicon Photonic Interconnected Chiplets With Computational Network And IMC For LLM Inference Acceleration (NUS)

A new technical paper titled “PICNIC: Silicon Photonic Interconnected Chiplets with Computational Network and In-memory Computing for LLM Inference Acceleration” was published by researchers at the ...
TweakTown

Dell PowerEdge XE9712: NVIDIA GB200 NVL72-based AI GPU cluster for LLM training, inference

Dell has just unleashed its new PowerEdge XE9712 with NVIDIA GB200 NVL72 AI servers, with 30x faster real-time LLM performance over the H100 AI GPU. Dell Technologies' new AI Factory with NVIDIA sees ...
Business Wire

Positron AI Secures $51.6 Million in Oversubscribed Series A to Accelerate Inference-Optimized Hardware

RENO, Nev.--(BUSINESS WIRE)--Positron AI, the premier company for American-made semiconductors and inference hardware, today announced the close of a $51.6 million oversubscribed Series A funding ...
ADTmag

Best practices to accelerate inference for large-scale production workloads

This ebook breaks down four techniques Together AI uses to optimize production inference: speculative decoding, optimized kernels, near-lossless compression, and hardware acceleration.
Digi Times

ByteDance open-sources COMET to boost MoE efficiency, accelerating LLM training by 1.7x

ByteDance's Doubao AI team has open-sourced COMET, a Mixture of Experts (MoE) optimization framework that improves large language model (LLM) training efficiency while reducing costs. Already ...
VentureBeat

How attention offloading reduces the costs of LLM inference at scale

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More Rearranging the computations and hardware used to serve large language ...
InfoWorld

Multi-token prediction technique triples LLM inference speed without auxiliary draft models

With reported 3x speed gains and limited degradation in output quality, the method targets one of the biggest pain points in production AI systems: latency at scale. High inference latency and ...
Virtualization Review

Running AI Natively on Windows 11 Using an eGPU

Even an older workstation-class eGPU like the NVIDIA Quadro P2200 delivers dramatically faster local LLM inference than CPU-only systems, with token-generation rates up to 8x higher. Running LLMs ...
Computer Weekly

Qualcomm gears up for AI inference revolution

Qualcomm’s answer to Nvidia’s dominance in the artificial acceleration market is a pair of new chips for server racks, the A1200 and A1250, based on its existing neural processing unit (NPU) ...
Semiconductor Engineering

Scheduling Architecture Integrated With M3D BEOL Memories For LLM Inference (Georgia Tech, Samsung)

A new technical paper titled “Architecting Long-Context LLM Acceleration with Packing-Prefetch Scheduler and Ultra-Large Capacity On-Chip Memories” was published by researchers at Georgia Institute of ...
InfoQ

Cactus v1: Cross-Platform LLM Inference on Mobile with Zero Latency and Full Privacy

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...