ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
Reviewed by Pithpith:545EKLHDopen to challenge →
read the original abstract
Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices. Despite recent trends favoring alternative activation functions such as GELU or SiLU, known for increased computation, this study strongly advocates for reinstating ReLU activation in LLMs. We demonstrate that using the ReLU activation function has a negligible impact on convergence and performance while significantly reducing computation and weight transfer. This reduction is particularly valuable during the memory-bound inference step, where efficiency is paramount. Exploring sparsity patterns in ReLU-based LLMs, we unveil the reutilization of activated neurons for generating new tokens and leveraging these insights, we propose practical strategies to substantially reduce LLM inference computation up to three times, using ReLU activations with minimal performance trade-offs.
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
GRINQH introduces a graded input-based quantization hierarchy that dynamically assigns multi-precision weights using activation magnitudes as importance proxy, unifying quantization with sparsification to improve LLM ...
-
Second-Order Path Kernel Interpolation Formulas in Machine Learning
Derives second-order path-kernel interpolation formulas for gradient descent, SGD, and momentum training, adding curvature terms and a concentration estimate around the expected prediction.
-
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
RT-Lynx shifts DiT sparsity from weights to activations, reports up to 1.55x linear-layer speedup while preserving generation quality across multiple diffusion models.
-
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
SPON adds learnable persistent activation anchors trained via distribution matching to restore LLM accuracy under high activation sparsity by preventing representational distribution shifts.
-
SiLIF: Structured State Space Model Dynamics and Parametrization for Spiking Neural Networks
SiLIF models apply SSM dynamics and parametrization to spiking neurons for stable training, reaching new SOTA on event-based and raw-audio speech datasets while using half the compute of SSMs via synaptic delays.
-
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
SPON adds a small set of trainable input-independent activation vectors as representational anchors, trained by distribution matching, to stabilize sparse activation in LLMs and recover performance lost to hidden-stat...
-
Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
Post-training N:M activation pruning preserves generative performance in LLMs better than equivalent weight pruning, with the 8:16 pattern emerging as a practical hardware-friendly choice.
-
PowLU: An Activation Function for Stable Pre-Training of LLMs
PowLU replaces SwiGLU with a rational-power activation to reduce outlier amplification and numerical instability during large-scale LLM pre-training while matching performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.