🚀 Meet LLaDA2.2-flash — the first agent-oriented MoE Diffusion LLM.
Levenshtein editing—deletion, insertion, and substitution—enables self-correction during decoding. A more elegant solution to model collapse than forcing diffusion back into left-to-order generation.
Performance:
⚡ 703.82 TPS on BFCL-V4 function calling
519.0 TPS on SWE-bench Verified coding
⚡ 1.64x BF16 throughput vs autoregressive models
Built for high-throughput, low-latency AI agents.
🔗 GitHub: https://t.co/3TJUYNSLdT
🤗 Hugging Face: https://t.co/8OrHXBiGp2
📄 Technical Report:https://t.co/liV6nOk8YU
#LLaDA #OpenSource #DiffusionLLM #AIAgents
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
tool use — A model's ability to call external functions — run code, search the web, edit files — instead of only generating text.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
Diffusion decoding with insert, delete and substitute edits offers a non autoregressive route to high throughput tool useA model's ability to call external functions — run code, search the web, edit files — instead of only generating text.Full definition →, with a reported 1.64x BF16 throughput advantage and open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → to verify it.
