Baidu's ECHO: multi-token prediction reusing the last layer as a drafter
xiaohu · x · 2026-11-11
ECHO is Baidu's multi-token prediction method: the model reuses its final layer to draft several subsequent tokens, which the full model verifies in one pass. Consecutive correct drafts emit multiple tokens per step, speeding up decoding. It's one of the inference acceleration techniques behind ERNIE 5.5 Flash Preview.
More from Models
- Google open-sources Harness², an agent that rewrites its own setup per task — Arindam_1729 · 2026-11-11
- Dev dumps Codex desktop app over quality issues, falls back to codex-cli — tekbog · 2026-11-11
- Why do old models get dumber before launches? Lab party, says joking X post — glcst · 2026-11-11
- Grok Bot now detects hidden prompt injections, warns users and refuses to follow them — XFreeze · 2026-11-11
- Shanghai Institute Open-Sources Nex-N2.6, a 321B Multimodal Agentic Model — victormustar · 2026-11-11
- Nex-N2.6 ships open FP8 weights (321B, GLM-5.3-Flash based), cuts reasoning loops 16%→1.6% — Physical_Hat4022 · 2026-11-11