anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Docs] Separate DLO transfer mode design

Browse Source 
Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
This commit is contained in:
Hongsheng Liu committed 2026-08-19 11:23:16 +08:00
1 parent 8f93a74951
commit 1ccdc2e80e
2 files changed
+225 -146
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/diffusion/offloader/distributed_layerwise_offload.md
+6 -3
View File
@@ -5,9 +5,12 @@ buffers instead of keeping the complete DiT in HBM. It supports sharded host
weights with AllGather or independently streamed rank-local weights. The
no-AllGather path can optionally share node-local runtime weights through mmap.
See the [DLO component architecture](../../../design/feature/offloader/distributed_layerwise_offload.md#architecture)
for ownership and lifecycle coordination, and the remaining feature design for
loader contracts, compatibility details, and failure handling.
See the [shared DLO component architecture](../../../design/feature/offloader/distributed_layerwise_offload.md#architecture)
for ownership and lifecycle coordination. The mode-specific internals are
documented separately in the
[AllGather design](../../../design/feature/offloader/distributed_layerwise_offload.md#allgather-design)
and
[no-AllGather design](../../../design/feature/offloader/distributed_layerwise_offload.md#no-allgather-design).
## Choose a mode