Roger WangandGao Han
a5800cd2c2
Signed-off-by: Roger Wang <hey@rogerw.io> Signed-off-by: Gao Han <gaohan19@huawei.com> Co-authored-by: Gao Han <gaohan19@huawei.com>
14 lines
311 B
Python
14 lines
311 B
Python
"""
|
|
DiT Cache Manager for vLLM-Omni.
|
|
|
|
This module provides caching functionality for DiT (Diffusion Transformer) models
|
|
to optimize inference performance and memory usage.
|
|
"""
|
|
|
|
|
|
class DiTCacheManager:
|
|
"""Manages DiT-specific caching for optimized inference."""
|
|
|
|
def __init__(self, config):
|
|
pass
|