3 posts tagged “speculative-decoding”
I built self-speculative decoding for MLX. On an M3, naive layer-skip never beats baseline — 24 configs, 24 losses
Self-speculative decoding lets a model draft its own tokens by skipping layers — speculative decoding's speedup with no extra memory. I built it for MLX and swept 24 configs on an M3. Every one was slower than baseline, even though all were lossless. Here's why, and the paper that fixes it.
Three ways to make an LLM read its weights less often on a Mac — and why each one backfires
Single-stream decoding on Apple Silicon is bottlenecked by reading the model's weights out of memory, not by the math. Three techniques attack that directly — speculative decoding, diffusion generation, and self-speculative layer-skipping. I measured all three on a 16 GB M3. Each is right in theory and backfires in its own way: the bottleneck just moves one step further from the arithmetic.
Speculative decoding on a 16 GB Mac: a 20% win that becomes a 25% loss
A 1B draft model speeds up Llama-3.1-8B by 20% on an M3 — at num_draft_tokens=2. Push that dial to 4 and decoding gets 25% SLOWER than using no draft at all. Here's the measured curve, and why low draft counts win when decode is bound by memory bandwidth.