Skip to content

fix dockerfile in devcontainer and fix expert torch #684

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
KMSorSMS merged 2 commits into from
Feb 26, 2025
Merged

fix dockerfile in devcontainer and fix expert torch #684

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
de082f1
:zap: fix cd error
KMSorSMS Feb 26, 2025
ffb86c6
:zap: fix experts torch
KMSorSMS Feb 26, 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
1 change: 0 additions & 1 deletion .devcontainer/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,6 @@ apt update -y && apt install -y --no-install-recommends \
g++ \
cmake &&
rm -rf /var/lib/apt/lists/* &&
cd ktransformers &&
pip install ninja pyproject numpy cpufeature &&
pip install flash-attn &&
cp /usr/lib/x86_64-linux-gnu/libstdc++.so.6 /opt/conda/lib/
Expand Down
6 changes: 3 additions & 3 deletions ktransformers/operators/experts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -459,9 +459,9 @@ def load(self, w: dict | nn.Parameter | tuple | None = None, device: str | None
self.up[i] = w["up"][i, ...].to(device=device, dtype=self.dtype)
self.down[i] = w["down"][i, ...].to(device=device, dtype=self.dtype)

self.up = torch.cat(self.up, dim=0)
self.gate = torch.cat(self.gate, dim=0)
self.down = torch.cat(self.down, dim=0)
self.up = torch.stack(self.up, dim=0)
self.gate = torch.stack(self.gate, dim=0)
self.down = torch.stack(self.down, dim=0)
return

def unload(self):
Expand Down