nvidia-specdecode-al-doctorlisted

# NVIDIA Speculative-Decoding AL/D Doctor ## When Speculative decoding, MTP, EAGLE, draft length, accept length, claimed speedup, SPEED-Bench AL talk. ## Do ```bash npx thumbgate nvidia-specdecode-al-doctor \ --speculative-decoding \ --accept-length=AL \ --draft-length=D \ --draft-depth-ratio=ρ \ --claimed-speedup=X \ --json ``` Pair with: ```bash npx thumbgate deepseek-v4-runtime-guardrails \ --speculative-decoding --accept-length=AL --draft-length=D \ --draft-depth-ratio=ρ --claimed-speedup=X --cache-coherence-eval --json ``` ## Never - Claim speedup without measured AL - Ship TensorRT-LLM / Model-Optimizer / EAGLE training clones - Treat missing AL as a pass