TLDRocket
Sign in
Latest Recursive launches Flint, a laptop coding model it says was largely bu... — TechCrunch While Amazon blocks AI agents, Walmart rolls out the welcome mat — TechCrunch NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Rela... — Hugging Face Physicist Christopher Stubbs joins Anthropic's Long-Term Benefit Trust — Anthropic How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77%... — Hugging Face Just Eat apologises for AI food mistakes after social media ridicule — BBC News How AT&T is rethinking in-house legal work with OpenAI — OpenAI SpaceX to attempt Starship catch on next flight, with eye on rapid cad... — Ars Technica

The AI intelligence platform

Every AI story that matters — and the intelligence behind it.

TLDRocket reads all relevant sources, removes duplicate coverage, and publishes a short neutral summary of every story, linking back to the original. Free, no spam, unsubscribe anytime.

Add to Slack

Every story also updates live profiles event timelines weekly rankings the AI Market Index

Thursday, 4 November 2021

Scaling up BERT-like model Inference on modern CPU - Part 2

Hugging Face 4 years ago 45

Intel's Ice Lake Xeon CPUs achieve up to 75% faster inference on NLP tasks compared to the previous Cascade Lake generation through hardware improvements like new instructions and PCIe 4.0 support. The performance gains come from software optimizations including Intel's oneAPI libraries (oneMKL, oneDNN, oneTBB) and framework-specific tuning of memory allocation, parallelization, and mathematical operators. Users can extract these improvements by enabling oneDNN in TensorFlow via an environment variable or through PyTorch's native integration, along with tuning parallelization settings like OpenMP configuration.

Read the full story

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.