[Bugfix] Surface all-rank diffusion RPC failures (#4403)

Signed-off-by: hsliuustc0106 <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu authored and GitHub committed 2026-06-13 15:42:16 +08:00
1 parent d75a6433b4
commit fa94f41807
6 files changed
+353 -56

No files matched your search

+19 -1
View File
@@ -18,6 +18,7 @@ import torch
from vllm_omni.diffusion.data import DiffusionOutput
_SHM_TENSOR_THRESHOLD = 1_000_000 # 1 MB
DIFFUSION_RPC_RESULT_ENVELOPE = "diffusion_rpc_result"
def _tensor_to_shm(tensor: torch.Tensor) -> dict[str, Any]:
@@ -130,15 +131,26 @@ def _pack_diffusion_fields(output: DiffusionOutput) -> DiffusionOutput:
return output
def _is_rpc_result_envelope(output: object) -> bool:
return isinstance(output, dict) and output.get("type") == DIFFUSION_RPC_RESULT_ENVELOPE
def pack_diffusion_output_shm(output: object) -> object:
"""Replace large tensors in diffusion worker outputs with SHM handles.
Supports either a bare ``DiffusionOutput`` or a wrapper object carrying one
in ``.result`` (for example ``RunnerOutput``).
in ``.result`` (for example ``RunnerOutput``), or an RPC result envelope
carrying the diffusion output in ``["result"]``.
"""
if isinstance(output, DiffusionOutput):
return _pack_diffusion_fields(output)
if _is_rpc_result_envelope(output):
result = output.get("result")
if isinstance(result, DiffusionOutput):
output["result"] = _pack_diffusion_fields(result)
return output
result = getattr(output, "result", None)
if isinstance(result, DiffusionOutput):
output.result = _pack_diffusion_fields(result)
@@ -158,6 +170,12 @@ def unpack_diffusion_output_shm(output: object) -> object:
if isinstance(output, DiffusionOutput):
return _unpack_diffusion_fields(output)
if _is_rpc_result_envelope(output):
result = output.get("result")
if isinstance(result, DiffusionOutput):
output["result"] = _unpack_diffusion_fields(result)
return output
result = getattr(output, "result", None)
if isinstance(result, DiffusionOutput):
output.result = _unpack_diffusion_fields(result)