Skip to content

[dist][moe] fix add moe_context for big models #2405

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kylesayrs merged 2 commits into from
Feb 25, 2026
Merged

[dist][moe] fix add moe_context for big models #2405

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6507355
[ddp][moe] fix add moe_context for big models
HDCharles Feb 25, 2026
14276bb
Merge branch 'main' into big_model_ddp_fix
HDCharles Feb 25, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions src/llmcompressor/modeling/moe_context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@
from abc import ABC

import torch
import torch.distributed as dist
from compressed_tensors.offload import is_distributed
from compressed_tensors.registry import RegistryMixin, standardize_lookup_name
from loguru import logger
from tqdm import tqdm
Expand Down Expand Up @@ -111,6 +113,8 @@ def moe_calibration_context(
)
model.set_submodule(name, replacement)
replaced[name] = (module, replacement)
if is_distributed():
dist.barrier()

# Log what was replaced
if replaced:
Expand Down