What if an LLM could EDIT its own tokens in real-time, not just generate them? 🤯
Introducing LLaDA2.1 — a diffusion model that breaks from autoregressive dominance. It drafts fast, then fixes its own mistakes on the fly with Token-to-Token editing.
The result? 892 tokens/sec on a 100B model. 🔥
⚡ 892 TPS on HumanEval+ (coding)
⚡ 801 TPS on BigCodeBench
🧠 Real-time self-correction via T2T editing
✅ @lmsysorg SGLang Day 0 support — production-ready now
A "non-consensus" architecture now challenging the mainstream. Open-sourced TODAY. 👇
#LLaDA #TokenEditing #OpenSource #LLM #dLLM
What's the secret? Our revolutionary Error-Correcting Editable (ECE) engine. 🧠
LLaDA2.1 doesn't just write; it drafts, then intelligently reviews and edits its own work, much like a human expert.
This two-phase approach fixes a major weakness of early diffusion models — exposure bias and error accumulation.
Flexibility is key. LLaDA2.1 introduces a dual-mode design:
⚡ Speedy Mode for rapid iteration and prototyping
💎 Quality Mode for precision-critical production tasks
You choose between speed and perfection based on your needs. From research to real-world applications.
We've also pioneered the first-ever large-scale Reinforcement Learning (RL) framework for a 100B-parameter diffusion model.
Through EBPO (Block-level Policy Optimization), LLaDA2.1 learns to understand and follow complex human instructions with incredible fidelity. It doesn't just generate, it understands. 🤝
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Diffusion LLMs now have a self-correction pass and day-zero SGLang support, so a 100B model reporting 892 tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → per second becomes a real option to test for latency-bound coding workloads.
Read the full thread on X ↗
