Skip to content

Fix DeepSeek PTQ script #912

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
cjluo-nv merged 1 commit into from
Feb 20, 2026
Merged

Fix DeepSeek PTQ script #912

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: 1 addition & 1 deletion examples/deepseek/ptq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ def linear(
weight = weight_quantizer(weight)
return F.linear(x, weight, bias)
elif gemm_impl == "bf16":
weight = weight_dequant(weight, weight.scale)
weight = weight_dequant(weight, weight.scale, dtype=torch.bfloat16)
if act_quantizer is not None:
x = act_quantizer(x)
if weight_quantizer is not None:
Expand Down
2 changes: 1 addition & 1 deletion examples/deepseek/quantize_to_nvfp4.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,11 +44,11 @@
from typing import Any

import torch
from ds_kernel import weight_dequant
from safetensors.torch import load_file, save_file
from tqdm import tqdm

from modelopt.torch.quantization.qtensor import NVFP4QTensor
from modelopt.torch.quantization.triton import weight_dequant


def _remap_key(key_dict: dict[str, Any]):
Expand Down