Efficient Transformers: A Survey
read the original abstract
Transformer model architectures have garnered immense interest lately due to their effectiveness across a range of domains like language, vision and reinforcement learning. In the field of natural language processing for example, Transformers have become an indispensable staple in the modern deep learning stack. Recently, a dizzying number of "X-former" models have been proposed - Reformer, Linformer, Performer, Longformer, to name a few - which improve upon the original Transformer architecture, many of which make improvements around computational and memory efficiency. With the aim of helping the avid researcher navigate this flurry, this paper characterizes a large and thoughtful selection of recent efficiency-flavored "X-former" models, providing an organized and comprehensive overview of existing work and models across multiple domains.
This paper has not been read by Pith yet.
Forward citations
Cited by 15 Pith papers
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio versions via TTS and noise, showing model-dependent performance with small text-to-voice gaps of 1.8-4.8 points on Confetti and When2Call.
-
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
FlashAttention-3 achieves 1.5-2x speedup on H100 GPUs for attention, reaching 740 TFLOPs/s (75% utilization) in FP16 and near 1.2 PFLOPs/s in FP8 while cutting numerical error by 2.6x versus baseline FP8 attention.
-
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Medusa augments LLMs with multiple decoding heads and tree-based attention to predict and verify several tokens in parallel, yielding 2.2-3.6x inference speedup via two fine-tuning regimes.
-
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
FlashAttention reduces GPU high-bandwidth memory accesses in self-attention via tiling, delivering exact attention with lower IO complexity, 2-3x wall-clock speedups on models like GPT-2, and the ability to train on s...
-
Perceiver IO: A General Architecture for Structured Inputs & Outputs
Perceiver IO is a general architecture that processes arbitrary structured inputs and outputs with linear scaling and achieves strong results on GLUE, Sintel optical flow, multi-task reasoning, and StarCraft II withou...
-
When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics
STS is a two-stage pruning framework that decouples structural diversity via repulsion sampling from semantic filtering via cross-attention to reduce redundancy in visual tokens for VLMs.
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance...
-
An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling
S4D state space models correspond exactly to wave propagation and nonlinear wave interactions in a one-dimensional ring oscillator network, with a closed-form operator describing the complete input-output map.
-
M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
M²RNN achieves perfect state tracking at unseen lengths and outperforms Gated DeltaNet hybrids by 0.4-0.5 perplexity on 7B models with 3x smaller recurrent states.
-
TiledAttention: a CUDA Tile SDPA Kernel for PyTorch
TiledAttention is a cuTile-based SDPA kernel that balances performance with Python-level customizability for attention research in PyTorch.
-
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.
-
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Mixture-of-Depths enables transformers to dynamically allocate compute by routing only the top-k tokens through each layer's full computations, matching baseline performance with a fraction of the FLOPs per forward pa...
-
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
-
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Deformable DETR achieves higher accuracy than DETR, especially on small objects, while converging in one-tenth the training epochs by using sparse deformable attention on image features.
-
Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation
Ligandformer is a self-attention graph neural network framework that predicts compound properties, outputs attention maps for local structural interpretation, and claims improved robustness and generalization over pri...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.