DFlash
DFlash is a speculative decoding method in which the draft model is a small block-diffusion network rather than an autoregressive one.
AI Inference
Explore AI Inference through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Diffusion Models
Articles that also belong to these categories. Counts cover all of AI Inference.
All articles (109)AI Hardware (30)AI Infrastructure (30)Large Language Models (20)Developer Tools (18)Open Source AI (15)Machine Learning (11)NVIDIA (11)AI Companies (9)Deep Learning (9)Training & Optimization (8)MLOps (7)Chinese AI (4)Model Architecture (4)Reasoning Models (4)AI Models (3)Algorithms (3)Meta AI (3)Reinforcement Learning (3)AI Alignment (2)Anthropic (2)Artificial Intelligence (2)Data Centers (2)Edge computing (2)Google (2)Information Retrieval (2)AI Benchmarks (1)AI Research (1)AI Safety (1)AI Tools & Products (1)Computer Science (1)Diffusion Models (1)Enterprise AI (1)Generative AI (1)Image Generation (1)Microsoft (1)Mixture of Experts (1)Natural Language Processing (1)OpenAI (1)People (1)Prompt Engineering (1)Small Language Models (1)Speech & Audio AI (1)Statistics (1)Transformer Models (1)Video Generation (1)
Showing 1-1 of 1 article