[Feat] Support MagCache (#1287)

Signed-off-by: Lancer <maruixiang6688@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
This commit is contained in:
authored and GitHub committed 2026-05-29 22:26:23 +08:00
1 parent eba5617c95
commit b690a10e3a
13 files changed
+1677 -11

No files matched your search

+2 -1
View File
@@ -5,6 +5,7 @@ Cache module for diffusion model inference acceleration.
This module provides a unified cache backend system for different caching strategies:
- TeaCache: Timestep Embedding Aware Cache for adaptive transformer caching
- MagCache: Magnitude-based Cache for adaptive transformer caching
- cache-dit: DBCache, SCM, and TaylorSeer caching strategies
Cache backends are instantiated directly via their constructors and configured via OmniDiffusionConfig.
@@ -26,9 +27,9 @@ from vllm_omni.diffusion.cache.teacache.backend import TeaCacheBackend
__all__ = [
"CacheBackend",
"TeaCacheConfig",
"CacheContext",
"TeaCacheBackend",
"TeaCacheConfig",
"apply_teacache_hook",
"PromptEmbedCache",
"install_prompt_embed_cache",