Enable Diffusion Image models asynchronous output (#4981)

Signed-off-by: zzh <943967662@qq.com>
Co-authored-by: dengyunyang <584797741@qq.com>
This commit is contained in:
zzhanddengyunyang authored and GitHub committed 2026-07-29 17:21:55 +00:00
1 parent f2d9eb1630
commit dba05c3517
22 files changed
+1440 -72

No files matched your search

+18
View File
@@ -190,6 +190,24 @@ class OmniPlatform(Platform):
def synchronize(cls) -> None:
raise NotImplementedError
# ── Async diffusion output: cross-stream sync ──
@classmethod
def record_device_event(cls):
"""Record a device event on the default stream to mark tensor readiness.
On platforms where distributed communication (e.g. HCCL) may use
internal streams not visible to the default stream, this method
should synchronize the default stream before recording the event
to ensure the event captures all completed work including
cross-device communication results.
Returns ``None`` by default so that platforms without a native
implementation (ROCm, XPU, MUSA) fall through to a safe no-op.
Override in platform subclasses to provide real event support.
"""
return None
@classmethod
def get_free_memory(cls, device: torch.device | None = None) -> int:
raise NotImplementedError