Skip to content

fix: detect GPU arch automatically for kernel building #169

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

Open
Dogacel wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: detect GPU arch automatically for kernel building #169

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b738115
fix: detect GPU arch automatically for kernel building
Dogacel May 17, 2026
9044eb1
remove "a" from sm
Dogacel May 18, 2026
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
24 changes: 24 additions & 0 deletions tokenspeed-kernel/python/setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -453,6 +453,30 @@ def _detect_cuda_archs(self):
archs.add(self._normalize_cuda_arch(direct))
return archs

# Try detecting from the NVIDIA driver.
if not archs:
try:
caps = (
subprocess.check_output(
[
"nvidia-smi",
"--query-gpu=compute_cap",
"--format=csv,noheader",
],
text=True,
stderr=subprocess.DEVNULL,
)
.strip()
.splitlines()
)
for cap in caps:
cap = cap.strip()
if cap:
archs.add(self._normalize_cuda_arch(cap + "a"))
Copy link
Copy Markdown
Contributor

@borontion borontion May 17, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

why there is a suffix "a" here - cap + "a". shouldn't it be handled by _normalize_cuda_arch?

Copy link
Copy Markdown
Author

@Dogacel Dogacel May 18, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am a bit confused, it seems like we can remove.

The goal was to get sm100a, sm90a, sm120a etc. The normalize does,

        suffix = "a" if has_suffix or major >= 9 else ""
        return f"{major}{minor}{suffix}"

So it will always has "a", BUT when I tried to compile tokenspeed on sm80, I never succeeded so I couldn't test.

So just removing it should result in identical code for supported architectures, I'll do that.

Copy link
Copy Markdown
Contributor

@lightseek-bot lightseek-bot May 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi we don’t plan to support sm80

except (OSError, subprocess.CalledProcessError):
pass

# Fallback: Blackwell
if not archs:
archs.add("100a")
return archs
Expand Down