central processing unit
PulseAugur coverage of central processing unit — every cluster mentioning central processing unit across labs, papers, and developer communities, ranked by signal.
9 天有情绪数据
-
LLM inference: CPU vs GPU trade-offs detailed for local deployments
This article explores the practical differences between CPU and GPU inference for large language models (LLMs) using the llama.cpp framework. It highlights that while GPUs offer superior speed, CPUs can be a viable alte…
-
Local LLM Setup Guides Detail llama.cpp Installation and Optimization
This series of guides provides comprehensive instructions for setting up and running large language models (LLMs) locally on Linux systems. It details hardware and software prerequisites, recommends using llama.cpp for …
-
New framework speeds up discrete optimization on GPUs
Researchers have developed a new CPU-GPU framework to accelerate optimization problems with discrete variables, which have historically been challenging for GPUs. This framework processes branch and bound nodes in batch…
-
Hesheng New Material confirms low CPU inventory at investee Yizhi Electronics
Hesheng New Material has confirmed that its investee company, Yizhi Electronics, is experiencing low CPU inventory and is planning to place new orders to restock. Yizhi Electronics, which is not controlled by Hesheng Ne…
-
AI investment shifts from GPU training to inference infrastructure
The AI industry's investment focus is shifting from GPU manufacturing for model training to the infrastructure required for inference. As AI tools become more integrated into daily operations, the demand for continuous …
-
Hengguang Information CPU hits 5.15GHz, entering domestic 5GHz era
Hengguang Information has achieved a new milestone with its next-generation terminal CPU, reaching a single-core frequency of 5.15GHz under extreme liquid nitrogen cooling. This achievement marks the first time a domest…
-
Agentic AI expands across industries, with IT pros reporting high adoption
Agentic AI is rapidly expanding its applications across various industries, with IT professionals reporting widespread adoption and identifying key use cases. Companies like Dell are focusing on balancing the safety and…
-
Ascend-RaBitQ system accelerates billion-scale vector search with NPU-CPU architecture
Researchers have developed Ascend-RaBitQ, a novel system designed to accelerate billion-scale vector similarity search by leveraging heterogeneous NPU-CPU architectures. This approach decouples coarse ranking on NPUs wi…
-
vLLM CPU backend setup detailed by new contributor
A new contributor to vLLM has documented challenges and solutions for setting up the project's CPU backend. The process requires specific GCC versions and hidden build dependencies like setuptools_scm, which are not cle…
-
CPUs are sufficient for most AI tasks, offering cost savings
Most AI applications do not require a GPU and can perform optimally using CPU infrastructure. This approach can be more cost-effective for businesses. The article provides guidance on how to integrate AI into applicatio…
-
Mac mini outperforms expensive workstations running large AI models
A $1,999 Mac mini equipped with Apple Silicon can run a 70-billion parameter AI model, outperforming a $4,000 Windows workstation. This is attributed to Apple's unified memory architecture, which eliminates VRAM and PCI…
-
PoTAcc pipeline accelerates power-of-two quantized DNNs on edge devices
Researchers have developed PoTAcc, an open-source pipeline designed to accelerate the deployment of power-of-two (PoT) quantized deep neural networks (DNNs) on resource-constrained edge devices. This system facilitates …
-
HCInfer system enables LLMs on resource-constrained devices with error compensation
Researchers have developed HCInfer, a novel inference system designed to enable large language models (LLMs) to run efficiently on devices with limited memory. This system offloads parts of the model's compensation mech…
-
Rongxin Zhiyuan raises hundreds of millions for GPU-centric AI architecture
Rongxin Zhiyuan, an AI infrastructure company founded by Tsinghua University alumni, has secured hundreds of millions of yuan in an angel funding round. The company is developing its novel AGC architecture, which positi…
-
AI image generation: CPU vs GPU performance and scaling insights
This article explores the performance differences between CPUs and GPUs when generating AI-created images and videos. The author shares their experience using these components for digital art creation, highlighting that…
-
Memory giants push new MRDIMM standard for AI, HPC servers
Major memory manufacturers Samsung Electronics, SK Hynix, and Micron are nearing completion of the next-generation server DRAM module standard, MRDIMM. This new standard is optimized for AI and high-performance computin…
-
RadLite fine-tunes small LLMs for CPU-deployable radiology AI
Researchers have developed RadLite, a method for fine-tuning small language models (SLMs) with 3-4 billion parameters for radiology tasks. This approach, utilizing LoRA fine-tuning on models like Qwen2.5-3B-Instruct and…
-
AMD stock surges to new high driven by AI chip demand
AMD's stock has reached a new peak, driven by the increasing demand for powerful computer chips essential for artificial intelligence applications. This surge reflects a significant shift in the central processing unit …
-
Intel, AMD hike CPU prices amid AI demand; shipping sector sees order surge
Demand for AI computing power has driven significant price increases for CPUs from AMD and Intel, with server CPUs seeing the largest jumps. This shortage is expected to persist through 2027, with further price hikes an…
-
China unveils Lingshen supercomputer, achieving 2 Exaflops with 47,000 CPU-only processors
China has unveiled plans for a new exascale supercomputer, named Lingshen, that will exclusively use domestically produced CPUs. This system will feature 47,000 processors across 92 cabinets, aiming for a peak performan…