TLDRocket
Sign in

AI Efficiency

132 summarised stories about AI Efficiency, each linking back to the original source. Browse all topics →

+ Follow this topic

Key players

NVIDIA OpenAI The New Stack Apple MarkTechPost Meta

Thursday, 17 September 2026

Intel squeezed a 1.58-bit LLM down to 1.485 bits without changing a single weight

The New Stack 4 weeks ago 11

Intel researchers introduced BITCOS to compress ternary LLM weights by storing zero locations separately, without retraining or changing model outputs. BITCOS reduced storage to 1.485 bits per weight and increased decoding throughput by up to 18% on CPUs and 27% on GPUs. The smaller format speeds token decoding on many Intel platforms but does not help on bandwidth-rich CPUs like Lunar Lake where a fixed 2-bit kernel stays faster.

Read the full story
GPU Infrastructure AI Efficiency Model Compression

The Sequence Opinion - Issue 935: Chinese Algorithmic Efficiency vs. American Scale in Frontier AI

TheSequence 1 month ago 50

The Sequence Opinion (Issue 935) argues that Chinese frontier labs emphasize algorithmic efficiency while American labs pursue scaling via major infrastructure plans like OpenAI’s Stargate, and that this is often misframed as “cleverness vs purchasing power.” Issue 935 is the specific edition cited. The focus shifts to how each side decides whether to spend the next dollar on more computation or on making existing compute more productive, which can change model design and what training runs are worth attempting.

Read the full story
AI Infrastructure OpenAI GPU Infrastructure AI Efficiency

Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers

MarkTechPost 1 month ago 5

Nunchux AI released VC-Attention, a training-free low-bit attention kernel aimed at speeding up video Diffusion Transformers by improving both low-bit value handling and the softmax stage. The writeup says attention takes more than 64% of generation time on an RTX 5090. The company reports that V-Smooth and ExpCast-FP8 cut pipeline cost enough to reduce one V-Smooth call from 42.2 ms to 4.8 ms on a B200 and lower attention-time overhead overall.

Read the full story
AI Infrastructure AI Efficiency Video Generation

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.