#D-Flash
5 related articles
·2 min
D-Flash: How Diffusion Drafting Delivers 3.5x Faster LLM Inference
D-Flash solves the autoregressive drafter latency bottleneck in speculative decoding via fast diffusion parallel drafting and target feature KV injection. 16 tokens in just 6ms, up to 3.5x speedup on HumanEval, beating EAGLE3 and MTP.
Read more →
·3 min
D-Flash: The Secret Behind 3.5x LLM Inference Speedup with Diffusion Drafting
D-Flash uses fast diffusion parallel drafting and target feature KV injection to solve the autoregressive Drafter latency bottleneck in speculative decoding. 16 tokens in just 6ms, up to 3.5x speedup on HumanEval, surpassing EAGLE3 and MTP.
Read more →
·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.
Read more →
·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.
Read more →
Tutorials·1 min
ESP-IDF Extension Integrates AI Agent: Complete Embedded Build, Flash, and Debug with Natural Language
ESP-IDF VS Code extension integrates Copilot Chat Agent mode, enabling natural language build, flash, and debug with AI-powered error analysis and fix suggestions.
Read more →