[Perf] Add reusable exact projection caching with MiniMax-H3 integration (#7987)

Signed-off-by: lishunyang12 <lishunyang12@users.noreply.github.com>
Signed-off-by: Armaan Amatya <armaanamatya2014@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@users.noreply.github.com>
Co-authored-by: Armaan Amatya <38102001+armaanamatya@users.noreply.github.com>
This commit is contained in:
authored and GitHub committed 2026-09-24 23:30:42 +08:00
1 parent 63bbd19a1d
commit 535bd35b42
11 files changed
+1886 -3

No files matched your search

+3 -1
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
"""
Cache module for diffusion model inference acceleration.
@@ -12,6 +12,7 @@ Cache backends are instantiated directly via their constructors and configured v
"""
from vllm_omni.diffusion.cache.base import CacheBackend
from vllm_omni.diffusion.cache.exact_projection_cache import ExactProjectionCache
from vllm_omni.diffusion.cache.prompt_embed_cache import (
PromptEmbedCache,
install_prompt_embed_cache,
@@ -27,6 +28,7 @@ from vllm_omni.diffusion.cache.teacache.backend import TeaCacheBackend
__all__ = [
"CacheBackend",
"ExactProjectionCache",
"CacheContext",
"TeaCacheBackend",
"TeaCacheConfig",