Mercury: Ultra-Fast Language Models Based on Diffusion
This addresses the need for faster inference in coding assistance tools, though it appears incremental as it applies diffusion to an existing domain.
The authors introduced Mercury, a diffusion-based large language model for coding applications that achieves state-of-the-art throughput of 1109 tokens/sec for the Mini version and 737 tokens/sec for the Small version on NVIDIA H100 GPUs, outperforming speed-optimized models by up to 10x while maintaining comparable quality.
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 frontier. 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 tokens/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 https://platform.inceptionlabs.ai/ and free playground at https://chat.inceptionlabs.ai