Tag

#latency

4 articles

Perplexity AI Open-Sources Unigram Tokenizer That Achieves 5x Lower p50 Latency Than Hugging Face tokenizers Crate

Perplexity AI open-sources a new Unigram tokenizer that reduces p50 latency by 5x and cuts CPU utilization by 5-6x compared to Hugging Face tokenizers.

May 2851

tech

Microsoft is boosting the launch time of key Windows apps and features - here's how

Microsoft is enhancing Windows 11's responsiveness with a new Low Latency Profile feature that speeds up app launches and interface interactions.

May 1149

tech

Speeding up agentic workflows with WebSockets in the Responses API

OpenAI introduces WebSocket-based optimizations for Codex agent workflows, reducing API overhead and improving model latency by up to 40%.

Apr 2260

Beyond Simple API Requests: How OpenAI’s WebSocket Mode Changes the Game for Low Latency Voice Powered AI Experiences

OpenAI's new WebSocket mode revolutionizes low-latency voice AI experiences by enabling real-time, continuous data streaming, significantly reducing delays in voice interactions.

Feb 23114