Skip to content

[executorch][cuda] Find the tuned INT4 kernel's def under its module-level name too #24103

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

Closed
pytorchbot wants to merge 1 commit into from
Closed

[executorch][cuda] Find the tuned INT4 kernel's def under its module-level name too #24103

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
9 changes: 5 additions & 4 deletions backends/cuda/tests/test_int4_quantized_gemm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
import contextlib
import os
import pickle
import re
import statistics
import tempfile
import types
Expand Down Expand Up @@ -887,10 +888,10 @@ def linear(x):
)
source = "\n".join(code)
name = autotuner.fn.fn.__name__
self.assertIn(f"def {name}(", source)
block = source[
source.rindex("user_autotune(", 0, source.index(f"def {name}(")) :
]
# A module-level kernel's def is renamed to Inductor's kernel name: name plus a suffix.
kernel_def = re.search(rf"^def {re.escape(name)}\w*\(", source, re.MULTILINE)
self.assertIsNotNone(kernel_def, source)
block = source[source.rindex("user_autotune(", 0, kernel_def.start()) :]
configs = block[: block.index("],")]
self.assertEqual(configs.count("'num_warps'"), 1)
_check_close(self, compiled, eager)
Expand Down
Loading