Your Local Throughput Just Doubled (With No Accuracy Tax)
Multi-token prediction is merged into llama.cpp, delivering 1.4–2.2x throughput on Qwen3.6 with zero accuracy loss.
#speculative-decoding
5 posts
DFlash Decode Collapses at Long Output. MTP Doesn't.
One llama.cpp flag—--spec-draft-p-min 0.75—turns MTP from a dud into a decode speed that holds flat across output lengths where DFlash falls apart.
Your vLLM Thinking Budget Was Doing Nothing With MTP On
vLLM 0.21.0 shipped Friday with a quiet fix: thinking_token_budget was being silently ignored when MTP speculative decoding was enabled. If you serve reasoning models with spec decode, you have been paying for it.
Your Local Qwen3.6 Throughput Probably Just Halved (and How to Fix It)
llama.cpp renamed the MTP flag on May 13. The old --spec-type mtp is silently ignored. If your tok/s dropped from 140 to 70 you are likely running without speculative decoding.
Speculative Decoding Explained: Why Your Local Model Got 2× Faster in 2026
The same Qwen3.6-27B that ran at 70 tokens/sec on a 4090 in January was running at 140 tokens/sec by April. Nothing changed about the model. Speculative decoding moved from research curiosity to default. Here is what it actually does.