Inception Labs Creates a Diffusion Based LLM

Mar 7 (edited) • 💬 General

Diffusion LLM a new model for language generation is faster than generative LLMs.

"""

We trained diffusion large language models that are up to 10x faster and cheaper than current LLMs, pushing the frontier of intelligence and speed for language model

1 We are announcing the Mercury family of diffusion large language models (dLLMs), a new generation of LLMs that push the frontier of fast, high-quality text generation.

2 Mercury is up to 10x faster than frontier speed-optimized LLMs. Our models run at over 1000 tokens/sec on NVIDIA H100s, a speed previously possible only using custom chips.

3 A code generation model, Mercury Coder, is available to test in a playground. We offer enterprise clients access to code and generalist models via an API and on-premise deployments.

"""

Speed Benchmarks in Image

19 comments