#ai-accelerators

[ follow ]

The HackerNoon Newsletter: Could Trump Make Crypto Great Again? (11/8/2024) | HackerNoon

AI accelerators are crucial for efficiently deploying Large Language Models (LLMs) at scale.

Primer on Large Language Model (LLM) Inference Optimizations: 2. Introduction to Artificial Intelligence (AI) Accelerators | HackerNoon

AI accelerators significantly enhance performance and reduce costs for deploying Large Language Models at scale.
#amd

AMD gun for Nvidia H200 with MI325X AI chips

AMD's MI325X AI accelerators feature 256 GB of HBM3e, enhancing performance for AI workloads while differentiating itself from Nvidia.

AMD's new Instinct GPUs might just blow Nvidia out of the water

AMD launches MI325x accelerators aimed at enhancing AI performance and efficiency, directly competing with Nvidia.

AMD now expects to sell $5bn worth of GPUs in 2024

AMD's Instinct MI300X AI accelerators are set to significantly increase revenue, projected at $5 billion for fiscal 2024.

The Register Kettle brews up over AMD's latest AI chips

AMD claims its MI300 is the fastest AI processing package on the market
Memory requirements and packaging are critical challenges in the AI accelerator market

AMD gun for Nvidia H200 with MI325X AI chips

AMD's MI325X AI accelerators feature 256 GB of HBM3e, enhancing performance for AI workloads while differentiating itself from Nvidia.

AMD's new Instinct GPUs might just blow Nvidia out of the water

AMD launches MI325x accelerators aimed at enhancing AI performance and efficiency, directly competing with Nvidia.

AMD now expects to sell $5bn worth of GPUs in 2024

AMD's Instinct MI300X AI accelerators are set to significantly increase revenue, projected at $5 billion for fiscal 2024.

The Register Kettle brews up over AMD's latest AI chips

AMD claims its MI300 is the fastest AI processing package on the market
Memory requirements and packaging are critical challenges in the AI accelerator market
moreamd
#china

China reportedly tells local AI buyers to ignore Nvidia

Chinese authorities are pushing for local AI accelerator procurement, favoring Huawei over Nvidia.

UAE calls US fears of China using region as AI proxy valid

China may be using Middle East countries to bypass US sanctions on machine learning accelerators.
US concerns about machine-learning accelerator chips reaching China via the Middle East are valid.

China reportedly tells local AI buyers to ignore Nvidia

Chinese authorities are pushing for local AI accelerator procurement, favoring Huawei over Nvidia.

UAE calls US fears of China using region as AI proxy valid

China may be using Middle East countries to bypass US sanctions on machine learning accelerators.
US concerns about machine-learning accelerator chips reaching China via the Middle East are valid.
morechina

IBM Cloud to offer Intel's Gaudi 3 AI chips next year | TechCrunch

Intel's Gaudi 3 AI accelerator will be offered by IBM Cloud, enhancing AI capabilities in hybrid and on-premise environments.
from Theregister
2 months ago

Tenstorrent details its RISC-V packed Blackhole chips

Tenstorrent's Blackhole AI accelerators claim superior performance and scalability compared to Nvidia A100, redefining chip performance in AI applications.

AI infrastructure hopefuls find unlikely ally in Qualcomm

Qualcomm partners with Ampere for AI infrastructure, leveraging AI 100 accelerators for large models and batch sizes.

Apple reportedly developing AI chips for servers

Apple is developing its custom AI accelerators for server chips named ACDC, building on its chip design experience and transitioning to its own Arm-compatible silicon.

New Huawei MateBook X Pro 2024 weighs just 980g, packs an Intel Core Ultra 9 processor

Lightweight and thin design, weighing only 980g and measuring 13.5mm.
Powerful performance with the new Intel Ultra 9 processor and Arc GPU, offering configurations to suit various budgets.

Intel Gaudi's third, final hurrah posited as H100 contender

Intel's Habana Gaudi3 AI accelerators aim to compete with Nvidia's H100 in training and inference tasks.
Habana Gaudi3 features a unique multi-die architecture with focus on AI workloads, distinct from traditional GPUs.

Nvidia's next-gen Blackwell platform will come to Google Cloud in early 2025 | TechCrunch

New instance types and accelerators announced at Google Cloud Next, emphasizing AI accelerators and custom chips.
Google and Nvidia partnership for A3 Mega instance and confidential A3 instance to enhance AI training and protect sensitive data.

Tens of thousands of GPUs go under-utilized in the cloud

Cloud providers are deploying a large number of GPUs and AI accelerators, but evidence suggests they are being under-utilized.
TechInsights estimates that in 2023 alone, 878,000 accelerators were responsible for $5.8 billion in revenue, but this figure could be much higher if clusters were operating closer to capacity.

Ongoing Saga: How Much Money Will Be Spent On AI Chips?

AI spending is extensive and complex to estimate accurately, with projections indicating substantial growth in AI accelerator market size.
Companies investing in AI accelerators and related chips face challenges in tracking utilization and performance of these technologies within systems.

Etched scores $120M for an ASIC built for transformer models

Etched is developing an inference chip, Sohu, specialized in serving transformer models, claiming a 20x performance advantage over Nvidia's H100 by focusing on a specific type of AI model.
[ Load more ]