AgentDish directory

speculative decoding

Accepted listings with this tag.

Listing	Category	Score	Trend	Checked
#1588 ↓ -2 Speculative Decoding in vLLM on AMD GPUs A detailed vLLM blog post explaining speculative decoding on AMD GPUs, with mechanics, supported drafting methods, configuration guidance, tuning advice, and benchmark discussion.	AI/ML / Inference Optimization	82	↓ -2	39 days ago	Details
#1914 ↓ -1 How to Setup a Local Coding Agent on macOS A detailed walkthrough for running a local coding agent on macOS with llama.cpp, Gemma 4, MTP speculative decoding, image support, and Pi as the agent interface.	Developer Tools / Code Assistant	80	↓ -1	125 days ago	Details
#2147 ↓ -384 Achieving 3X speedups on Google TPUs with diffusion-style speculative decoding Google Developers Blog post about integrating DFlash, a diffusion-style speculative decoding framework, into the vLLM TPU ecosystem to improve LLM serving speed on TPU v5p.	Developer Tools / Code Assistant	78	↓ -384	163 days ago	Details
#2195 → 0 Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding arXiv paper on a self-speculative decoding framework for speeding up reasoning LLM inference on edge hardware, with hardware co-design and reported speedups.	Research / AI/ML Paper	77	→ 0	140 days ago	Details
#2279 → 0 DSpark: Speculative decoding accelerates LLM inference A DeepSeek paper about DSpark, a full-stack codebase for training and evaluating speculative decoding algorithms to speed up LLM inference.	Developer Tool / AI Infrastructure	75	→ 0	110 days ago	Details