Skip to content

低内存模式下设备不一致问题 #179

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
yghstill merged 3 commits into from
Dec 22, 2025
Merged

低内存模式下设备不一致问题 #179

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f0e60b9
fix(awq): 修复低内存模式下设备不一致问题
imleoo Dec 19, 2025
a30971a
fix(awq): 将block移动到最佳设备以修复潜在性能问题
imleoo Dec 19, 2025
578d24e
docs: 删除CLAUDE.md文件
imleoo Dec 19, 2025
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
7 changes: 5 additions & 2 deletions angelslim/compressor/quant/modules/awq/search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,7 @@ def search_by_block(
best_ratio = -1
best_scales = None
dev = get_best_device()
block.to(dev)
with torch.no_grad():
if cache is not None:
origin_out = torch.ones_like(act)
Expand Down Expand Up @@ -97,7 +98,8 @@ def search_by_block(
if layer.weight.dtype == torch.float8_e4m3fn:
w = weight_dequant(layer.weight, layer.weight_scale_inv)
layer.weight.data = w
layer.weight.mul_(scales.view(1, -1))
# Fix for low_memory mode: ensure scales is on same device as weights
layer.weight.mul_(scales.to(layer.weight.device).view(1, -1))
if type(layer) in self.observer_layer_classes:
quant_dequant_weight = pseudo_quantize_tensor(
layer.weight,
Expand Down Expand Up @@ -130,7 +132,8 @@ def search_by_block(
best_scales = scales

for layer, w in zip(layers, org_w):
layer.weight.data = w.to(act.device)
# Fix for low_memory mode: restore weights to GPU, not act.device
layer.weight.data = w.to(dev)

origin_out = origin_out.detach().cpu()
new_out = w.detach().cpu()
Expand Down
Loading