> ## Documentation Index > Fetch the complete documentation index at: https://lmsysorg-dsv4-1.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Caching Acceleration > Compare caching acceleration strategies for diffusion models. SGLang provides three complementary caching strategies for Diffusion Transformer (DiT) models. All reduce denoising cost by skipping redundant computation, but they operate at different levels. ## Overview SGLang supports three complementary caching approaches:

Strategy	Scope	Mechanism	Best For
Cache-DiT	Block-level	Skip individual transformer blocks dynamically	Advanced, higher speedup
TeaCache	Timestep-level	Skip entire denoising steps based on L1 similarity	Simple, built-in
Spectrum	Timestep-level	Forecast DiT features to skip selected denoising steps	Experimental, model-validated tuning

## Cache-DiT [Cache-DiT](https://github.com/vipshop/cache-dit) provides block-level caching with advanced strategies like DBCache and TaylorSeer. It can achieve up to **1.69x speedup**. See [Cache-DiT](./cache_dit) for detailed configuration. Cache-DiT currently cannot be combined with `--use-fsdp-inference`. Keep FSDP disabled when enabling Cache-DiT. DiT layerwise offload is compatible: skipped blocks are not streamed, and the first layer after a skip may sync-load. ### Quick Start ```bash theme={null} SGLANG_CACHE_DIT_ENABLED=true \ sglang generate --model-path Qwen/Qwen-Image \ --prompt "A beautiful sunset over the mountains" ``` ### Key Features * **DBCache**: Dynamic block-level caching based on residual differences * **TaylorSeer**: Taylor expansion-based calibration for optimized caching * **SCM**: Step-level computation masking for additional speedup ## TeaCache TeaCache (Temporal similarity-based caching) accelerates diffusion inference by detecting when consecutive denoising steps are similar enough to skip computation entirely. See [TeaCache](./teacache) for detailed documentation. ### Quick Overview * Tracks L1 distance between modulated inputs across timesteps * When accumulated distance is below threshold, reuses cached residual * Uses separate positive/negative caches for supported CFG model families ### Supported Models * Wan2.1 * Z-Image * Wan2.2: coefficients are not calibrated yet; enabling TeaCache is accepted but currently no-ops * HunyuanVideo: not supported yet For Flux and Qwen models, TeaCache is automatically disabled when CFG is enabled. ## Spectrum Spectrum forecasts DiT features and skips selected denoising steps. It is approximate and currently applies only to selected native implementation paths. See [Spectrum Acceleration](./spectrum) for supported model families, constraints, and request controls. ## References * [Cache-DiT Repository](https://github.com/vipshop/cache-dit) * [TeaCache Paper](https://arxiv.org/abs/2411.14324)