Skip to main content

Share story

AI

Inco AI releases DFlash 2 speculative-decoding drafters

DFlash 2: Keep Drafting Parallel Image: Primary
Inco AI released DFlash 2 drafters for Qwen3.8-27B and Meta's Muse Glimmer. The company says the software improves parallel speculative decoding by selecting among candidate tokens and adding block-local dynamic convolutions. Inco reports average benchmark gains of 16% to 25% over its earlier DFlash approach and says the combined changes add 1.3% to draft-verify cycle latency. Those performance results are company-reported.
Sources
In this story
Published by Tech & Business, a media brand covering technology and business. This story was sourced from Inco and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
AI
AI

Meta releases code to connect Muse with custom hardware

Meta released open source code that lets builders connect its Muse AI agent to their own hardware, The Verge reported. The SDKs support off-the-shelf ESP32 boards and Raspberry Pi devices, with connections to displays, buttons, se...

AI Security
AI Security

Apple plans stricter consent controls for macOS Full Disk Access

Apple announced plans to require more explicit user action before apps receive macOS Full Disk Access, citing growing risks from autonomous AI agents, TechCrunch reported. The setting permits access to files, mail, messages and br...

AI Capital
AI Capital

Relay raises $36M for AI communications used by frontline workers

Relay raised $36M to help businesses capture information from frontline work, SiliconANGLE reported. The startup develops cloud-hosted radio communicators powered by AI for frontline workers. Relay says its aim is to capture what ...