Conscious Engines
The Need for Speed: Why LLMs Are Slow and What Speculation Promises
Your GPU sits nearly idle during token generation — the memory-bandwidth bottleneck behind LLM latency, and how speculation exploits it.
Inference
Read more →Research and Development
Experiments in model architecture, training, evaluation, and efficient inference
Featured
All research
Speculative Decoding, Formally: The Algorithm, the Proof, and the Metrics That Matter
Conscious Engines
The draft-then-verify algorithm behind speculative decoding, its rejection-sampling proof of losslessness, and the metrics that matter.
Inference
The Need for Speed: Why LLMs Are Slow and What Speculation Promises
Conscious Engines
Your GPU sits nearly idle during token generation — the memory-bandwidth bottleneck behind LLM latency, and how speculation exploits it.
Inference
A Field Guide to Speculative Decoding Methods
Conscious Engines
Every major speculative decoding method compared: Medusa, lookahead, SpecInfer, Sequoia, self-speculation, and more, mapped in one guide.
Inference
The EAGLE Family: Speculating in Feature Space
Conscious Engines
Three generations of EAGLE speculative decoding, from feature-level drafting to state-of-the-art speedups — compared side by side.
Inference
Parallel Drafting with Block Diffusion: DFlash and DDTree
Conscious Engines
DFlash and DDTree fill an entire token block per drafting pass, pushing speculative decoding speedups past 7x over sequential drafters.
Inference
Putting It to Work: Serving Speculative Decoding with vLLM and SGLang
Conscious Engines
A practical guide to enabling EAGLE, n-gram, and Medusa speculative decoding in vLLM and SGLang, with real production speedup numbers.
Inference
Speculative Decoding in MLX using DFlash
Sabesh B
An empirical evaluation of speculative decoding on Apple Silicon, across a 300-run parameter sweep
apple siliconInference