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 Model, Speeding Decoding up to 3.18x(5 posts)→
More from Infra
- Large data centers employ only ~50-150 permanent on-site staff, Microsoft says — brezina · 2026-10-16
- Prediction: Opus 5.5-level models on laptops by 2027, backed by Qwen 27B data — cephaloform · 2026-10-16
- Oracle down 12% in a week, nearly 50% off June high as OpenAI exposure spooks market — alvelda · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Microsoft Research unveils Magnetar, the fastest zkVM at 10-39x speedups and post-quantum security — jedisct1 · 2026-10-16
- Bonsai 2 2B hits 120 tok/s on iPhone 18 Pro, outpaces Qwen 3.5 2B at half the memory — cephaloform · 2026-10-16