Skip to content

fix ctx for convert v1-v2 v2-v1 using in_place tensor mutation #1962

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
merged 1 commit into from
Oct 1, 2025
Merged

fix ctx for convert v1-v2 v2-v1 using in_place tensor mutation #1962

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions gptqmodel/utils/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,6 +576,7 @@ def convert_gptq_v1_to_v2_format_module(module: BaseQuantLinear, bits: int, pack
module.qzero_format(format=2)

# Optionally convert weight from gptq_v1 to v2 format if Kernel is compatible with v2
@torch.inference_mode()
def convert_gptq_v1_to_v2_format(
model,
cfg: QuantizeConfig,
Expand Down Expand Up @@ -651,6 +652,7 @@ def convert_gptq_v2_to_v1_format_module(
module.qzero_format(format=1)

# Optionally convert weight from gptq_v2 to v1 export format if Kernel is compatible with v2
@torch.inference_mode()
def convert_gptq_v2_to_v1_format(
model,
quantize_config: QuantizeConfig,
Expand Down
4 changes: 2 additions & 2 deletions tests/models/test_qwen3_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@ class TestQwen3Moe(ModelTest):
DEBUG = True
ACT_GROUP_AWARE = True
DESC_ACT = False
DATASET_SIZE = 1024
DATASET_SIZE = 1024 * 4
DATASET_SORT = "desc"
QUANT_BATCH_SIZE = 4
QUANT_BATCH_SIZE = 8

def test_mimo(self):
self.quant_lm_eval()