#dspark

The latest AI and developer news about #dspark, with the original source and a short summary.

Speculative Decoding Speeds Up LLMs by Shifting GPU Work from Memory-Bound to Compute-Bound

Speculative decoding accelerates LLM inference by increasing total FLOPs to utilize idle compute resources, shifting the workload from memory-bound to compute-bound at low batch sizes.

·1·2026.10.08 09:00

llama.cpp Adds Support for DSpark Speculative Decoding

The open-source llama.cpp project has added a DSpark-based Speculative Decoding feature.

·1·2026.07.28 20:00

DeepSeek Open-Sources New Framework 'DSpark' That Boosts LLM Inference Speed by Up to 85%

DeepSeek has released DSpark, a speculative decoding framework that dramatically improves LLM response speed, under the MIT license.

·1·2026.06.30 09:00

DSpark: Speculative Decoding Framework Combining Semi-Autoregressive Generation and Confidence Scheduling Unveiled

DSpark unveiled a speculative decoding framework that combines semi-autoregressive generation with confidence scheduling to solve the sharp acceptance rate decline problem of parallel drafters.

·1·2026.06.28 09:00