# Inco AI releases DFlash 2 speculative-decoding drafters

_Wednesday, August 19, 2026 at 4:28 PM EDT · AI · Latest · Tier 2 — Notable_

![Inco AI releases DFlash 2 speculative-decoding drafters — Primary](https://inco.ai/og/dflash2.png)

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

- [Hacker News: Front Page](https://inco.ai/blog/dflash2/)

---
Canonical: https://techandbusiness.org/newswire/ufXslsNAll_LhDjR5oAg-x
Retrieved: 2026-08-20T01:26:44.229Z
Publisher: Tech & Business (techandbusiness.org)