[BugFix] Enable CPU offloading and Cache-DiT together on Diffusion Model (#1723)

Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com>
Signed-off-by: yuanheng <jonathan.zhaoyh@gmail.com>
This commit is contained in:
Yuanheng Zhao authored and GitHub committed 2026-03-09 22:25:41 +08:00
1 parent 7271116973
commit 82f63a4403
5 files changed
+67 -28

No files matched your search

@@ -27,7 +27,12 @@ def inference(model_name: str, offload: bool = True):
torch.cuda.reset_peak_memory_stats(device=device_index)
monitor = GPUMemoryMonitor(device_index=device_index, interval=0.02)
monitor.start()
m = Omni(model=model_name, enable_cpu_offload=offload)
m = Omni(
model=model_name,
# TODO: we might want to add overlapped feature e2e tests
# cache_backend="cache_dit",
enable_cpu_offload=offload,
)
torch.cuda.reset_peak_memory_stats(device=device_index)
height = 256
width = 256