Skip to content

fix(context): resolve amd-smi path in get_gpu_renderD_nodes (ROCM-27727) #156

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
coketaste merged 1 commit into from
Jul 15, 2026
Merged

fix(context): resolve amd-smi path in get_gpu_renderD_nodes (ROCM-27727) #156

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
4 changes: 3 additions & 1 deletion src/madengine/core/context.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -796,8 +796,10 @@ def get_gpu_renderD_nodes(self) -> typing.Optional[typing.List[int]]:
else:
# Modern method using amd-smi (ROCm >= 6.4.0)
# Get list of GPUs from amd-smi (redirect stderr to filter warnings)
# Use resolved path since /opt/rocm*/bin is not guaranteed to be on PATH
# Longer timeout (180s) for slow GPU initialization on SLURM compute nodes
output = self.console.sh("amd-smi list -e --json 2>/dev/null || amd-smi list -e --json 2>&1", timeout=180)
amd_smi_path = os.path.join(self._rocm_path, "bin", "amd-smi")
output = self.console.sh(f"{amd_smi_path} list -e --json 2>/dev/null || {amd_smi_path} list -e --json 2>&1", timeout=180)
Comment thread
coketaste marked this conversation as resolved.
if not output or output.strip() == "":
raise ValueError("Failed to retrieve AMD GPU data from amd-smi")

Expand Down