[Diffusion] Integrate no-AllGather DLO with Host Weight Runtime (#6486)

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Signed-off-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
Co-authored-by: hsliuustc0106 <hsliuustc0106@users.noreply.github.com>
This commit is contained in:
Hongsheng Liuandhsliuustc0106 authored and GitHub committed 2026-08-25 08:03:53 +08:00
1 parent 8fdb719a41
commit 8360346a66
27 files changed
+1640 -51

No files matched your search

@@ -362,6 +362,35 @@ def test_serve_cli_forwards_distributed_offload_residency():
assert engine_args["dlo_resident_layers"] == 20
def test_serve_cli_forwards_hwr_policy_for_no_allgather_dlo():
parser = TrackingArgumentParser()
subparsers = parser.add_subparsers(dest="command")
OmniServeCommand().subparser_init(subparsers)
args = parser.parse_args(
[
"serve",
"MiniMaxAI/MiniMax-H3",
"--omni",
"--enable-distributed-layerwise-offload",
"--dlo-no-use-allgather",
"--host-weight-runtime-mode",
"preferred",
"--host-weight-runtime-root",
"/var/cache/vllm-omni/hwr",
]
)
explicit_kwargs = args.get_explicit_kwargs_dict()
stage_cfg = AsyncOmniEngine._create_default_diffusion_stage_cfg(explicit_kwargs)[0]
engine_args = stage_cfg["engine_args"]
assert explicit_kwargs["host_weight_runtime_mode"] == "preferred"
assert explicit_kwargs["host_weight_runtime_root"] == "/var/cache/vllm-omni/hwr"
assert engine_args["host_weight_runtime_mode"] == "preferred"
assert engine_args["host_weight_runtime_root"] == "/var/cache/vllm-omni/hwr"
def test_serve_cli_accepts_diffusion_compile_controls():
"""Ensure both compile controls reach the diffusion stage."""
parser = TrackingArgumentParser()