+
+
+ +▼ code +▼ output + ▶ uv-logs + | +Cell: nv | 0.07s | FAILED + | + +Raw +
+
+
+
+1 +2 +3 +
+
+
import subprocess
+
+print(subprocess.run(["nvidia-smi"], capture_output=True, text=True).stdout)
+
+ +
+
+
+
+
+
Traceback (most recent call last): + File "/home/runner/work/kernels-uvnotes/kernels-uvnotes/moe_benchmarks/megablocks_yamoe/.uvnote/cells/nv.py", line 3, in <module> + print(subprocess.run(["nvidia-smi"], capture_output=True, text=True).stdout) + ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/subprocess.py", line 548, in run + with Popen(*popenargs, **kwargs) as process: + ^^^^^^^^^^^^^^^^^^^^^^^^^^^ + File "/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/subprocess.py", line 1026, in __init__ + self._execute_child(args, executable, preexec_fn, close_fds, + File "/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/subprocess.py", line 1955, in _execute_child + raise child_exception_type(errno_num, err_msg, err_filename) +FileNotFoundError: [Errno 2] No such file or directory: 'nvidia-smi' +
+
+
+ +

Comparison of Megablocks and Yamoe Kernels

+

This note compares the performance of the Megablocks and Yamoe kernels on the GPT-OSS-20B model.

+

Megablocks kernel

+

Yamoe Kernel

+