cd /news/machine-learning/speculative-decoding-collapses-at-ba… · home topics machine-learning article
[ARTICLE · art-83135] src=pub.towardsai.net ↗ pub= topic=machine-learning verified=true sentiment=· neutral

Speculative Decoding Collapses at Batch 224 on Llama-3-70B and Never on gpt-oss-120B

A 180-line roofline model built by an independent developer shows speculative decoding on Llama-3-70B collapses at batch 224, turning a 1.92x speedup into a 0.74x slowdown by batch 512, while the same technique on gpt-oss-120b, a mixture-of-experts model with a similar weight footprint, maintains efficiency until batch 1,981. The analysis highlights a 45x difference in crossover points, contradicting published benchmarks from vLLM that report up to 1.5x speedup at low QPS but 1.4x slowdown at high QPS on Llama-3-70B.

read1 min views1 publishedAug 1, 2026
Speculative Decoding Collapses at Batch 224 on Llama-3-70B and Never on gpt-oss-120B
Image: Pub (auto-discovered)

Member-only story

I built a 180-line roofline model of speculative decoding this week, and the number that fell out of it is batch 224. That is where speculative decoding stops being a 1.92x speedup on a dense Llama-3–70B and starts being a tax. By batch 512 the model says you are running at 0.74x — you have paid for a draft model, a bigger KV allocation, and a more complicated serving stack in order to serve 26% fewer tokens per second.

Then I ran the same model on gpt-oss-120b, a mixture-of-experts model with almost exactly the same weight footprint. The crossover moved to batch 1,981. Same technique, same hardware class, same draft budget. A 45x difference in where the feature turns on you.

The reason this matters is that the published record on speculative decoding openly contradicts itself, and almost every “should I enable this?” blog post cites one half of it.

The contradiction nobody reconciles #

Here is the actual state of the evidence.

vLLM’s own blog post, October 2024, is the canonical warning. On Llama-3–70B with a Qwama-0.5B drafter on 4xH100, they measured up to a 1.5x speedup at QPS=1 — and at high QPS, “we see 1.4x slowdown Llama3–70B on ShareGPT with 4xH100, 1.8x slowdown

── more in #machine-learning 4 stories · sorted by recency
── more on @llama-3-70b 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/speculative-decoding…] indexed:0 read:1min 2026-08-01 ·