Liquid AI Releases DSpark Draft Models for Up to 3.18x Faster Decoding
JosephJacks_ · x · 2026-08-21
Liquid AI has released DSpark draft models (300M params) for the LFM2.5 series, utilizing speculative decoding. By having a small model propose candidates and a large model verify them, it achieves up to 3.18x decoding speedup on H100 (MATH500) and 2.87x on M4 Max. The technique ensures output remains identical under greedy decoding without compromising accuracy, and is now supported by llama.cpp and SGLang.
Related event: Liquid AI Releases DSpark Draft Model, Speeding Decoding up to 3.18x(5 posts)→
More from Infra
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- vLLM ships Day-0 LoRA RL for Muse Spark Open, lifting AIME from 0.56 to 0.85 — vllm_project · 2026-10-16
- DSpark draft model for Muse Spark Open proposes 7 tokens per pass with 23-42% acceptance — vllm_project · 2026-10-16
- Cloudflare Stream's WebRTC ultra-low-latency live streaming is now Generally Available — ritakozlov · 2026-10-16
- YC-backed Overshoot launches inference optimization, claims $5M saved for AI teams — ycombinator · 2026-10-16