DFlash 2: Keep Drafting Parallel

DFlash 2 is the successor to our widely deployed parallel drafter: close to 3× the speed of autoregressive decoding, with the same output. Drafters for Qwen3.8-27B and Meta's Muse Glimmer are out today.
83 points by mike-the-brain 63 days ago inco.ai 12 comments

Summary

DFlash 2 significantly increases drafting speed, achieving nearly three times the efficiency of traditional autoregressive methods while maintaining output quality. New drafters for Qwen3.8-27B and Meta’s Muse Glimmer are now available.

Comments (12 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open