[Diffusion] Register HWR mmap for direct DLO H2D (#6591)

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 23:30:11 +08:00
1 parent 5a8b81ebeb
commit c608910d20
28 files changed
+1869 -153

No files matched your search

+25
View File
@@ -113,6 +113,22 @@ def validate_host_weight_runtime_options(*, mode: object, root: object) -> None:
raise ValueError("enabled Host Weight Runtime requires host_weight_runtime_root")
def validate_dlo_host_registration_options(
*,
limit_gib: object,
enable_dlo: bool,
use_allgather: bool,
hwr_mode: object,
) -> float:
"""Validate the optional transport budget without probing CUDA or HWR."""
value = float(limit_gib)
if not math.isfinite(value) or value < 0:
raise ValueError("dlo_host_registration_limit_gib must be finite and >= 0")
if value and (not enable_dlo or use_allgather or hwr_mode == "disabled"):
raise ValueError("dlo_host_registration_limit_gib requires enabled no-AllGather DLO and Host Weight Runtime")
return value
def parse_kv_cache_skip_selector(
selector: str | list[int] | tuple[int, ...] | set[int] | None,
) -> set[int] | None:
@@ -784,6 +800,9 @@ class OmniDiffusionConfig:
# existing loader/storage path.
host_weight_runtime_mode: str = "disabled"
host_weight_runtime_root: str | None = None
# Optional per-worker ceiling for registering final-layout HWR mappings.
# Zero adds no ceiling; pin_cpu_memory controls whether registration is tried.
dlo_host_registration_limit_gib: float = 0.0
pin_cpu_memory: bool = True # Use pinned memory for faster transfers when offloading
@@ -1164,6 +1183,12 @@ class OmniDiffusionConfig:
mode=self.host_weight_runtime_mode,
root=self.host_weight_runtime_root,
)
self.dlo_host_registration_limit_gib = validate_dlo_host_registration_options(
limit_gib=self.dlo_host_registration_limit_gib,
enable_dlo=self.enable_distributed_layerwise_offload,
use_allgather=self.dlo_use_allgather,
hwr_mode=self.host_weight_runtime_mode,
)
if self.diffusion_load_format != "diffusers" and (self.diffusers_load_kwargs or self.diffusers_call_kwargs):
raise ValueError(