⚡️Mercury: Ultra-Fast Diffusion LLMs — Estefano Ermon, CEO Inception Labs
Автор: Latent Space
Загружено: 2025-08-04
Просмотров: 2588
https://arxiv.org/abs/2506.17298
We present Mercury, a new generation of commercial-scale large language models (LLMs) based on diffusion. These models are parameterized via the Transformer architecture and trained to predict multiple tokens in parallel. In this report, we detail Mercury Coder, our first set of diffusion LLMs designed for coding applications. Currently, Mercury Coder comes in two sizes: Mini and Small. These models set a new state-of-the-art on the speed-quality fron- tier. Based on independent evaluations conducted by Artificial Analysis, Mercury Coder Mini and Mercury Coder Small achieve state-of-the-art throughputs of 1109 tokens/sec and 737 to- kens/sec, respectively, on NVIDIA H100 GPUs and outperform speed-optimized frontier models by up to 10x on average while maintaining comparable quality. We discuss additional results on a variety of code benchmarks spanning multiple languages and use-cases as well as real-world validation by developers on Copilot Arena, where the model currently ranks second on quality and is the fastest model overall. We also release a public API at platform. inceptionlabs. ai and free playground at chat.inceptionlabs.ai.
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
![[State of Post-Training] From GPT-4.1 to 5.1: RLVR, Agent & Token Efficiency — Josh McGrath, OpenAI](https://imager.clipsaver.ru/botHQ7u6-Jk/max.jpg)
![[State of AI Papers 2025] Fixing Research with Social Signals, OCR & Implementation — Team AlphaXiv](https://imager.clipsaver.ru/T0mZJjl_dsA/max.jpg)
![[State of Code Evals] After SWE-bench, Code Clash & SOTA Coding Benchmarks recap — John Yang](https://imager.clipsaver.ru/MxB-xRGXxkk/max.jpg)
![[State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual](https://imager.clipsaver.ru/tSRqTerZrH8/max.jpg)
