REVIEW 35 cited by
FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
read the original abstract
Diffusion transformers (DiT) have become the de facto choice for generating high-quality images and videos, largely due to their scalability, which enables the construction of larger models for enhanced performance. However, the increased size of these models leads to higher inference costs, making them less attractive for real-time applications. We present Fast-FORward CAching (FORA), a simple yet effective approach designed to accelerate DiT by exploiting the repetitive nature of the diffusion process. FORA implements a caching mechanism that stores and reuses intermediate outputs from the attention and MLP layers across denoising steps, thereby reducing computational overhead. This approach does not require model retraining and seamlessly integrates with existing transformer-based diffusion models. Experiments show that FORA can speed up diffusion transformers several times over while only minimally affecting performance metrics such as the IS Score and FID. By enabling faster processing with minimal trade-offs in quality, FORA represents a significant advancement in deploying diffusion transformers for real-time applications. Code will be made publicly available at: https://github.com/prathebaselva/FORA.
Forward citations
Cited by 35 Pith papers
-
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
-
ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
-
Test-time Sparsity for Extreme Fast Action Diffusion
Test-time sparsity with a parallel pipeline and omnidirectional feature reuse accelerates action diffusion by 5x to 47.5 Hz while cutting FLOPs 92% with no performance loss.
-
SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking
SpecEdit accelerates diffusion-based image editing up to 10x by using a low-resolution draft to identify edit-relevant tokens via semantic discrepancies for selective high-resolution denoising.
-
1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation
1.x-Distill achieves better quality and diversity than prior few-step distillation methods at 1.67 and 1.74 effective NFEs on SD3 models with up to 33x speedup.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB benchmark shows that embedding models' performance on traditional retrieval does not transfer to long-horizon memory tasks, larger models do not always perform better, and LMEB measures capabilities orthogonal to MTEB.
-
DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
DisCa replaces heuristic feature caching with a lightweight learnable neural predictor compatible with distillation, achieving 11.8× acceleration on video diffusion transformers with preserved generation quality.
-
FeatFix: Reuse What You Verify through Local Exact-Feature Correction for Faster Cached Diffusion Inference
Forwarding the already-computed exact feature at verification sites—instead of discarding it—improves diffusion generation quality at matched compute and reaches up to 6.70× speedup when wrapped around aggressive caches.
-
CODA: Algorithm-Hardware Co-design for Edge Video Diffusion via NMP-Enabled Compute-Cache Operator Disaggregation
Disaggregating cache operators from compute and overlapping them across the two classifier-free-guidance branches turns cross-timestep caching into up to 1.80x real end-to-end speedup on edge GPUs when the cache overf...
-
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
SyncCache accelerates DiT-based audio-driven portrait animation up to 4.12x via spatially-asymmetric probing and modality-decoupled caching while preserving near-lossless quality and audio sync.
-
SAFE-DiT: Semantics-Aware Fast-path Execution for High-Resolution Diffusion Transformers
SAFE-DiT accelerates DiT inference at high resolutions by eliding mask-induced dispatch tax in attention while preserving semantics via selective scheduling, delivering up to 5x speedup and large memory savings with v...
-
NaviCache: Test-Time Self-Calibration Caching for Video Generation
A test-time Kalman-style dual-state tracker of the output-to-input feature ratio enables error-bounded computation skipping in video diffusion without offline calibration.
-
LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
LearniBridge learns shared low-rank calibration updates via LoRA to enable high-ratio feature caching in DiTs using only 3-5 samples, delivering up to 5.87x acceleration on FLUX with quality gains on video models.
-
ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE
ReCache learns recomputation schedules via policy gradients to maximize quality under a target compute budget for any caching mechanism in diffusion models.
-
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.
-
FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
FIS-DiT achieves 2.11-2.41x speedup on video DiT models in few-step regimes with negligible quality loss by exploiting frame-wise sparsity and consistency through a training-free interleaved execution strategy.
-
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
FlashClear delivers up to 122x faster object removal than prior diffusion models via adversarial step distillation and asymmetric attention caching while preserving visual quality.
-
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
FlashClear achieves up to 8.26x speedup over its base diffusion model and 122x over OmniPaint for image object removal via region-aware adversarial distillation and foreground-prioritized caching while claiming to mai...
-
Motion-Aware Caching for Efficient Autoregressive Video Generation
MotionCache accelerates autoregressive video generation up to 6.28x by motion-weighted cache reuse based on inter-frame differences, with negligible quality loss on SkyReels-V2 and MAGI-1.
-
DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
A learnable cost predictor plus dynamic programming allocates layer-wise token sparsity for diffusion transformers, removing forced full steps and cutting ~54% compute on PixArt-α without quality loss.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB is a new benchmark of 193 retrieval tasks spanning episodic, dialogue, semantic, and procedural memory on which top embedding models score about 61 NDCG@10, largely uncorrelated with MTEB.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB is a 22-dataset, 193-task zero-shot benchmark showing that long-horizon memory retrieval is hard, not solved by scale, and largely orthogonal to MTEB passage-retrieval skill.
-
Block-wise Adaptive Caching for Accelerating Diffusion Policy
BAC accelerates transformer-based Diffusion Policy up to 3x by block-level adaptive feature caching using an Adaptive Caching Scheduler and Bubbling Union Algorithm to control error propagation.
-
Evolving Cache Schedules for Fast Diffusion Policy Inference
A training-free evolutionary search over global cache schedules cuts diffusion-policy inference FLOPs by up to 8x with near-full rollout success.
-
ACID: Adaptive Caching for vIDeo generation
ACID dynamically switches caching thresholds based on drift-signal rate of change, recovering near-conservative quality at substantially higher video-diffusion inference speeds.
-
ACID: Adaptive Caching for vIDeo generation
Adaptive threshold switching on the drift signal's rate of change expands the quality-vs-speed Pareto frontier of TeaCache, EasyCache, and DiCache across HunyuanVideo, Wan 2.1, and CogVideoX.
-
NaviCache: Test-Time Self-Calibration Caching for Video Generation
NaviCache re-conceptualizes feature changes in video diffusion as an INS problem with dual-state estimation and uncertainty-aware updates to enable accurate test-time computation skipping.
-
ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration
ResilPhase accelerates DiT inference via stable ODE macro-trajectory extrapolation with derivative-free barycentric Lagrange extrapolator and bounded phase mapping, claiming SOTA fidelity at high acceleration ratios o...
-
BeCARE: Budgeted Cache Refresh for Diffusion Transformer Acceleration
SoftCap introduces a Trajectory Drift Observer and Soft-Budget PI Controller for adaptive full-step triggering in DiT caching, reporting better ImageReward and LPIPS than SpeCa at similar FLOPs on FLUX.1-dev.
-
BeCARE: Budgeted Cache Refresh for Diffusion Transformer Acceleration
A feedback controller that gates full versus cached Transformer steps using drift risk and a soft compute budget improves FLUX.1-dev quality at matched compute over fixed caching policies.
-
DiSC: Resolution-Scalable Acceleration of Diffusion Models by Exploiting Sparsity and Cached Token Reuse with Hash-based Distribution
DiSC accelerates DiT and PixArt-Sigma diffusion models 3.47-4.74x over A100 GPUs by reusing cached tokens across denoising steps and reusing sparsity masks in attention, using hash-based bank distribution to run spars...
-
Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
Focused Forcing is a training-free per-frame KV selection method that combines attention scores with diversity metrics and head-importance estimation to accelerate autoregressive video diffusion up to 1.48x while impr...
-
Motion-Aware Caching for Efficient Autoregressive Video Generation
MotionCache speeds up autoregressive video generation by 6.28x on SkyReels-V2 and 1.64x on MAGI-1 via motion-weighted cache reuse based on inter-frame differences, with negligible quality loss on VBench.
-
AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers
AdaCorrection adaptively corrects offset caches in DiT inference via on-the-fly spatio-temporal validity checks to maintain near-original FID with moderate acceleration.
-
Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
Sparse ActionGen accelerates diffusion policies up to 4x for robot control via rollout-adaptive pruning and zig-zag activation reuse without performance loss.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.