#semi-autoregressive

8 related articles

Jul 25, 2026·2 min

DSpark: DeepSeek Partners with Peking University to Open-Source Inference Acceleration, Boosting Speed by Up to 85%

DeepSeek partners with Peking University to open-source DSpark, an inference acceleration tech boosting single-user speed by 57%-85% under high concurrency. Learn its three core designs and the DSpec framework.

Jul 25, 2026·2 min

DSpark: DeepSeek and Peking University Open-Source Inference Acceleration Tech with Up to 85% Speed Boost

DeepSeek and Peking University open-source DSpark, an inference acceleration tech boosting single-user generation speed by 57%-85% under high concurrency. Learn its 3 core designs and the DSpec framework.

Jul 22, 2026·4 min

DeepSeek Open-Sources DeepSpec: A Full-Stack Breakdown of Speculative Decoding

DeepSeek open-sources DeepSpec, a full speculative decoding training and evaluation toolkit featuring three draft model algorithms (Ego3, DeepFlash, DeepSpark), 12 checkpoints, MIT license, and 60–85% real-world speedup.

Jul 17, 2026·4 min

DSpark Open Source: DeepSeek's Inference Acceleration Tech That Doubles LLM Speed

DeepSeek and Peking University open-source DSpark, an inference acceleration technology using semi-autoregressive architecture and dynamic scheduling to boost LLM speed by 50%+ and double GPU concurrency without quality loss.

Jul 16, 2026·3 min

DeepSeek Open-Sources DSpark: 50%–400% LLM Inference Speedup Without Retraining

DeepSeek open-sources DSpark, delivering 50%–400% LLM inference speedup with no retraining or quantization, via semi-autoregressive drafting and confidence-scheduled verification.

Jul 13, 2026·3 min

The Rise of Diffusion Language Models: DiffusionGemma Crushes Autoregressive Models in Speed Tests

Diffusion language model DiffusionGemma dramatically outpaces autoregressive Deepseek Flash in speed tests. Explore the tech behind diffusion vs. autoregressive models and their challenges.

Jul 10, 2026·5 min

DeepSeek Boosts Inference Speed by 85%: How Speculative Decoding Is Reshaping the AI Speed Race

DeepSeek and Peking University's DS Spark paper boosts AI inference speed by up to 85% via confidence scheduling and semi-autoregressive speculative decoding — no model or GPU changes.

Jul 7, 2026·3 min

DeepSeek Open-Sources DiSpark: Up to 85% Faster AI Inference Without Changing Hardware

DeepSeek and Peking University release DiSpark, an open-source framework that speeds up LLM inference by 60–85% using speculative decoding and hierarchical verification — no hardware changes or retraining required.