{"type": "article", "title": "Speculative Decoding Collapses at Batch 224 on Llama-3-70B and Never on gpt-oss-120B", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/speculative-decoding-collapses-at-batch-224-on-llama-3-70b-and-never-on-gpt-oss", "original_source": "https://pub.towardsai.net/speculative-decoding-collapses-at-batch-224-on-llama-3-70b-and-never-on-gpt-oss-120b-623812c763de?source=rss----98111c9905da---4", "published": "2026-08-01T16:32:19+00:00", "accessed": "2026-08-01", "id": "speculative-decoding-collapses-at-batch-224-on-llama-3-70b-and-never-on-gpt-oss"}