[Feature] Add native ModelExpress weight transfer backend (#58399)

Signed-off-by: Hyunjae Woo <hwoo@nvidia.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
This commit is contained in:
Hyunjae Woo
2026-10-02 02:29:35 +00:00
committed by GitHub
co-authored by aoshen02
parent 785b990116
commit 5a661487e2
5 changed files with 558 additions and 0 deletions
+1
View File
@@ -36,6 +36,7 @@ engine drives on your behalf:
| [sparse_nccl](nccl.md#sparse-nccl) | NCCL broadcast | Checkpoint-coordinate sparse weight patches |
| [sharded_rdt](sharded_rdt.md) | NIXL / Ray Direct Transport (pull-based) | Very large models where each worker needs only its own slice (MoE with expert parallelism) |
| [nccl_m2n](m2n.md) | NCCL M2N reshard | Trainer and inference use different sharding layouts |
| [ModelExpress](modelexpress.md) | ModelExpress version-based transfer | Install immutable published weight versions, including object-storage checkpoints and deltas |
## Quickstart