SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.05955 · 2024

Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Exploiting activation sparsity is a promising approach to significantly accelerating the inference process of large language models (LLMs) without compromising performance. However, activation sparsity is determined by activation functions, and commonly used ones like SwiGLU and GeGLU exhibit limited sparsity. Simply replacing these functions with ReLU fails to achieve sufficient sparsity. Moreover, inadequate training data can further increase the risk of performance degradation. To address these challenges, we propose a novel dReLU function, which is designed to improve LLM activation sparsity, along with a high-quality training data mixture ratio to facilitate effective sparsification. Additionally, we leverage sparse activation patterns within the Feed-Forward Network (FFN) experts of Mixture-of-Experts (MoE) models to further boost efficiency. By applying our neuron sparsification method to the Mistral and Mixtral models, only 2.5 billion and 4.3 billion parameters are activated per inference iteration, respectively, while achieving even more powerful model performance. Evaluation results demonstrate that this sparsity achieves a 2-5x decoding speedup. Remarkably, on mobile phones, our TurboSparse-Mixtral-47B achieves an inference speed of 11 tokens per second. Our models are available at \url{https://huggingface.co/PowerInfer}

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2406.05955")
get_code_for_paper("2406.05955")
have("2406.05955")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2406.05955.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2406.05955.svg)](https://syntology.ai/paper/2406.05955)

Connect an agent — have() is free.