Skip to content

[OMNIML-6228] Run the GPTQ Hessian dp-sync test on the pooled gloo workers #3064

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
shengliangxu merged 1 commit into from
Oct 27, 2026
Merged

[OMNIML-6228] Run the GPTQ Hessian dp-sync test on the pooled gloo workers #3064

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 2 additions & 6 deletions tests/unit/torch/quantization/test_gptq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,11 +17,9 @@

import copy
import warnings
from functools import partial

import pytest
import torch
from _test_utils.torch.distributed.utils import spawn_multiprocess_job

import modelopt.torch.quantization as mtq
from modelopt.torch.quantization.utils import calib_utils
Expand Down Expand Up @@ -200,11 +198,9 @@ def _gptq_hessian_dp_sync_helper(rank, size, token_counts):
torch.testing.assert_close(helper.hessian, ref)


def test_gptq_hessian_dp_sync(skip_on_windows):
def test_gptq_hessian_dp_sync(cpu_dist_workers):
"""Token-weighted merge over a gloo (CPU) group, with one rank that saw no tokens."""
spawn_multiprocess_job(
2, partial(_gptq_hessian_dp_sync_helper, token_counts=(5, 0)), backend="gloo"
)
cpu_dist_workers.run(_gptq_hessian_dp_sync_helper, token_counts=(5, 0))


def test_a_calibration_run_forgets_earlier_forward_measurements(monkeypatch):
Expand Down
Loading