#speculative decoding
Speculative Decoding: 11 AI articles covering speculative decoding news, analysis, and research
Articles
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for⭐8
Liquid AI releases LFM2.5-VL-3B-DSpark, a speculative decoding drafter for its vision-language model, delivering up to 3.13x faster decoding on Apple silicon, w...
Jina AI Releases jina-ocr-v1: A 3.4B MoE Document Parser With⭐8
Jina AI releases jina-ocr-v1, a 3.4B MoE document parser with built-in speculative decoding, scoring 91.14 on OmniDocBench and built for low-budget GPUs.
X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative⭐8
X-CoSD enables lossless, communication-efficient collaborative speculative decoding across heterogeneous SLM–LLM vocabularies, improving token generation speed ...
TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based⭐10
TreeGraft enables adaptive multi-drafter speculative decoding, boosting LLM inference speed by 15.1% across benchmarks.
Speculative Decoding on CPUs: Nearly 4x Faster Token Generation⭐10
Speculative decoding with DFlash accelerates CPU token generation up to 3.92x on Qwen3.5-9B, cutting costs by 74%. Learn how vLLM makes it possible.
Liquid AI Unveils LFM2.5-DSpark Draft Models: Up to 3.18x Faster⭐7
Liquid AI's DSpark draft models speed up LFM2.5 inference by up to 3.18x on H100, with identical outputs. Self-hosted deployment, open license for small firms.
Meta AI Unveils Muse Glimmer: A 30B Open-Weight Agentic Model⭐7
Meta’s Muse Glimmer is a 30B open-weight agentic model running on a single consumer GPU via 4-bit compression and speculative decoding.
DeepSeek Unveils DeepSeek-V4-Flash-0731: Major Agentic and⭐8
DeepSeek launches V4-Flash-0731 with DSpark speculative decoding and Responses API, boosting agentic workflows and coding speed.
Tencent Open-Sources AngelSpec: A Unified Training Framework for⭐8
Tencent open-sources AngelSpec, a unified training framework for speculative decoding draft models, supporting MTP and block-parallel DFlash architectures
DeepSeek Releases DSpark: A Speculative Decoding Framework That⭐7
DeepSeek releases DSpark, a speculative decoding framework boosting DeepSeek-V4 per-user generation speed by 60–85% over MTP-1, with open-source availability.