Liquid AI Releases DSpark: Up to 3.18x Throughput via Speculative Decoding

JosephJacks_ · x · 2026-08-21

Liquid AI released DSpark draft models for the LFM2.5 series, introducing a speculative decoding path. This method uses a lightweight draft model to propose candidate tokens, which the target model verifies in a single forward pass, significantly boosting speed with minimal memory overhead. Benchmarks show up to 3.18x throughput increase on H100 and 2.87x on M4 Max, without compromising output quality.

Related event: Liquid AI Releases DSpark Draft Models for Up to 4x Faster Inference(3 posts)→

Original post →

More from Infra

Infra channel →